Gaurav Surtani

AI Engineer, Product Builder · San Francisco Bay Area

AI engineer with eight years in full-stack, data and ML engineering, building LLM applications. Currently the founding and sole engineer on DeepLearning.AI's three AI recruiting products.

  1. Since 2018: Enthralltech, Accenture, LIBS, Ascendion, San Jose State, NASA Ames, Bexorg, Tassel, DeepLearning.AI
  2. LLM applications at Bexorg, Tassel, DeepLearning.AI and Blog2Podcast
  3. At DeepLearning.AI: AI technical interviewer, recruiter sourcing and review tool, Valence Career Agent

About

More

I build LLM applications. At DeepLearning.AI I am the founding and sole engineer on three AI recruiting products: an AI technical interviewer used in live hiring, a recruiter sourcing and review tool, and a candidate-facing career agent. Before that I built data and AI tools at Bexorg and Tassel, and flight-path analysis at NASA Ames.

Building now

  • Career agentBuildinghelps candidates find their next role and returns a growth report
  • Sourcing toolIn usemigrated from Railway to AWS with zero-downtime deploys
  • AI interviewerIn useeach score shows the quote it came from
  • Jobs collectorBuilttracks careers pages at 1,400+ companies, 99,000+ jobs collected
  • gaurav-osRunningrefreshes itself every ten minutes
Education
MS, Artificial Intelligence, San Jose State University

Experience

2018 – now

Sep 2025 – Present · San Francisco Bay Area

DeepLearning.AI

Sep 2025 – Present

Founding AI Engineer · San Francisco Bay Area

  • Built the AI technical interviewer used in live hiring. It scores candidates on what they say, and each score shows the quote it came from, so a recruiter can check it.
  • Built and maintain the recruiter sourcing and review tool: migrated it from Railway to AWS with zero-downtime deploys, added bulk actions for 1,000 candidates, and cut LLM scoring costs.
  • Designed and built the Valence Career Agent, which helps candidates find their next role: it learns their goal, background and job constraints, runs a technical assessment, and returns a growth report with a positioning statement, answer coaching and a three-part growth plan.
  • Built a job-data pipeline tracking careers pages at 1,400+ companies, with 99,000+ jobs collected and 78,000+ live, to power role recommendations.
  • Exposed the sourcing tool as a scoped API for internal tools, and published dlai-mcp-server on npm for searching DeepLearning.AI courses from Claude Code, Codex and Cursor.
Projects 4AI Technical Interviewer · Recruiter Sourcing and Review Tool · Valence Career Agent · dlai-mcp-server

Projects 4

  • AI Technical Interviewer

    Structured technical interviews, graded from the transcript.

  • Recruiter Sourcing and Review Tool

    Candidate sourcing, scoring and review for the recruiting team.

    • Moves up to 1,000 candidates through a hiring stage at once with bulk actions.
    • Serves other internal tools through a scoped API.
  • Valence Career Agent

    Shows job seekers where they stand and what to work on next.

    • Starts from the candidate's goal (finding their next job, navigating their career, improving their AI skills, or preparing for interviews) and adapts the conversation to it.
    • Imports their résumé, LinkedIn and GitHub for them to review, then asks only what it does not know: career history, projects, pay, timing, location, visa constraints and non-negotiables.
    • Returns a growth report that coaches two or three answers (what worked, what to add) and sets three growth areas, each with an action, a deliverable and a success signal, all cited from the transcript.
    • Supports real-time voice and dictation, and lets candidates own their career snapshot and conversation record, with export and deletion.
  • dlai-mcp-server

    An MCP server for the DeepLearning.AI course catalog.

    • Exposes three tools (search_courses, get_course_details, list_topics) across 121 courses and 38 topics.
    • Has its source on GitHub.

Stack Python · TypeScript · Gemini · Claude · FastAPI · Next.js · PostgreSQL · Redis · AWS ECS · Terraform · Playwright · LLM Evaluation · Real-time Voice · MCP Protocol

Mar 2026 – Present · blog2podcast.com

Mar 2026 – Present

Founder, side project · blog2podcast.com

  • Built and run a pipeline that turns engineering blogs from 15 companies into daily AI-narrated podcasts.
Projects 1blog2podcast.com

Projects 1

  • blog2podcast.com

    Turns a tech blog post into a podcast: content extraction, script generation and text-to-speech.

    • Crawls the engineering blogs of companies such as Uber, Meta, Netflix and Airbnb on a daily schedule (APScheduler).
    • Extracts content with several strategies (trafilatura, with a BeautifulSoup fallback) and scores its quality.
    • Writes a source-grounded summary and a two-speaker script with Ollama Cloud, then voices it with Kokoro on CPU.
    • First version: GPT-5.2 scripts and OpenAI TTS, with parallel TTS generation in AsyncIO, 3-5x faster for 20-segment podcasts.
    • Takes user submissions: paste any URL or text and get a podcast in minutes.
    • Rebuilt the frontend in one day across 28 PRs: auth, player, navigation, library, search and PWA.
    • Works as a PWA with offline support, lock-screen controls (MediaSession API), iOS safe areas, dvh viewport, WCAG 2.5.8 touch targets, maskable icons and a service worker.
    • Covers the app with 34 E2E tests across 4 device profiles.

Stack Next.js · FastAPI · Ollama Cloud · Kokoro TTS · SQLite · Playwright · Railway · APScheduler · trafilatura · BeautifulSoup · PWA · MediaSession API

Jun 2025 – Sep 2025 · Remote

Tassel

Jun 2025 – Sep 2025

Full Stack AI Engineer · Remote

  • Built a video pipeline that segments graduation ceremony recordings by student and delivers personalized clips to 2M+ students, an $8M+ revenue opportunity.
  • Built a multi-agent transliteration chain on OpenAI that converts each student's name into its native-language script, so an ElevenLabs native voice pronounces it correctly in ceremony announcements.
  • Moved heavy Azure pipelines from always-on to on-demand scaling, cutting costs 40% and processing 8x faster.
Projects 2Multilingual Name Pronunciation · Graduation Video Pipeline

Projects 2

  • Multilingual Name Pronunciation

    Getting every graduate's name right in ceremony announcements, in any language.

    • Closed the gap left by ElevenLabs text-to-speech, which on its own mispronounced many students' names from other languages.
  • Graduation Video Pipeline

    Personalized graduation ceremony clips at scale.

    • Architected the Azure infrastructure behind it.

Stack Azure · Python · OpenAI · ElevenLabs · FFmpeg · Voice AI · TTS · Video Processing

May 2024 – May 2025 · New Haven, CT

Bexorg

May 2024 – May 2025

Full Stack AI Engineer · New Haven, CT

Applied NLP extraction and computer vision for medical imaging, with ChromaDB and the Gemini API.

  • Built a natural-language analytics tool that turns plain-English questions into Plotly and D3 dashboards, cutting analysis time 75%; a key sales differentiator that helped convert pilots to contracts.
  • Built a real-time data visualization platform on Neo4j and BigQuery with role-based access for 40+ users, cutting retrieval time 45%.
  • Built an ML quality-control system for time-series data with real-time anomaly detection, reducing data issues 70%.
  • Resolved critical pipeline bottlenecks, improving throughput 10x and enabling new enterprise customers.
Projects 4GenAI Query Canvas · Interactive Data Viewer · Time Series Analysis & QC · Team Collaboration Calendar

Projects 4

  • GenAI Query Canvas

    Natural language to visualization, with GenAI.

    • Built automatic chart selection and customization in Plotly and D3.
    • Added feedback-based learning that improved query accuracy 40% over time.
  • Interactive Data Viewer

    Real-time data visualization on Plotly, Flask, Neo4j Aura and BigQuery.

    • Built graph visualization in vis.js for exploring complex relationships in real time.
    • Built a graph-based unified data access layer with GNNs and optimized graph algorithms.
    • Designed interactive dashboards with real-time updates, improving data analysis efficiency 60%.
    • Added audit logging to the role-based access, for users across departments.
  • Time Series Analysis & QC

    Time-series analysis and quality control.

    • Built a visualization engine for time-series data that sped up pattern identification 55%.
    • Routed automated alerts by severity, cutting response time 80%.
    • Created quantitative QC scores for quality assessment and trend analysis.
  • Team Collaboration Calendar

    Async communication and experiment scheduling.

    • Built an async-first calendar that cut experiment deployment time from 7 days to 3-4 hours.
    • Built an automated scheduling engine that cut 1:1 meetings 60%.
    • Added real-time experiment tracking with automated status updates and notifications.
    • Integrated Slack and Jira for cross-functional teams.

Stack React · Node.js · Python · FastAPI · Flask · LangChain · GPT · Gemini API · ChromaDB · Next.js · TypeScript · Plotly · D3.js · vis.js · Neo4j · BigQuery · Docker · Kubernetes · REST APIs · GraphQL · Tailwind CSS

Dec 2023 – Mar 2024 · Mountain View, CA

NASA Ames Research Center

Dec 2023 – Mar 2024

Machine Learning Developer · Mountain View, CA

  • Analyzed flight-path adherence to air traffic control procedures with GeoPandas and Pyproj, identifying navigation patterns that informed aviation fuel-cost optimization.
  • Automated data validation across 1,000+ flight paths, reducing manual verification from 4 hours to 15 minutes, and containerized the legacy analysis system.
Projects 1Flight Path Optimization System

Projects 1

  • Flight Path Optimization System

    Flight-path analysis and adherence checks with Python, Pyproj, Xmitree and Folium.

    • Converted flight paths from lat/long to Cartesian coordinates with Pyproj, for web maps in Folium.
    • Built interactive visualization dashboards for airspace data in Folium, Leaflet.js and Plotly.
    • Containerized the legacy system, cutting setup for new researchers from days to minutes.
    • Built a time-series view of each flight path for real-time adherence analysis.

Stack Python · GeoPandas · Pyproj · Folium · Leaflet.js · Next.js · Plotly · Docker · AWS · NumPy · Pandas · Kubernetes · Geospatial Analysis · Data Visualization · Microservices

Jul 2023 – Feb 2024 · San Jose, CA

San Jose State University

Jul 2023 – Feb 2024

Research Assistant · San Jose, CA

  • Built ML models for spatial analytics, with exploratory analysis in R (dplyr, ggplot2) and hypothesis testing.
  • Built a multilingual NLP translation system (1 to 25 languages) with LangChain and HuggingFace.
Projects 3Sensor Fusion & Motion Planning · OHANA Mental Health Support · Multilingual TTS Research

Projects 3

  • Sensor Fusion & Motion Planning

    Camera and LiDAR fusion for motion planning.

    • Built a real-time sensor fusion pipeline combining LiDAR and camera data from the KITTI dataset.
    • Improved normalization to filter non-critical data, raising object detection accuracy.
    • Combined YOLO v8 with LiDAR data for precise 3D bounding boxes.
    • Built a multi-dimensional representation of the fused data for motion planning.
  • OHANA Mental Health Support

    A React web app for mental health support and hurricane relief in Hawaii.

    • Fine-tuned BERT and GPT-2 models on mental health data for emotional support, crisis response and a Q&A interface.
    • Added geolocation to find the nearest mental health centers and hospitals.
  • Multilingual TTS Research

    Research and evaluation of multilingual text-to-speech.

    • Evaluated TTS systems for 25+ languages, including Coqui TTS and Firefox voice synthesis.
    • Built a prototype interface to test and compare TTS implementations.
    • Created an evaluation framework for voice quality and language support.

Stack Python · R · LangChain · HuggingFace · React · Node.js · TypeScript · BERT · GPT-2 · YOLO v8 · OpenCV · Tailwind CSS · Wix CMS · Strapi · REST APIs

Dec 2021 – Aug 2023 · Basking Ridge, NJ

Ascendion (formerly Collabera)

Dec 2021 – Aug 2023

Software Engineer → Senior Software Engineer · Basking Ridge, NJ

Collabera became Ascendion during this role: Software Engineer from Dec 2021, then Senior Software Engineer from Nov 2022 to Aug 2023.

  • Mentored 20 engineers and ran 500+ code reviews, improving team code quality 35%.
  • Architected a data visualization system that processes 10M+ records for enterprise dashboards.
  • Built executive dashboards in D3.js and Highcharts, speeding up decision-making 75%.
  • Named Employee of the Quarter at Collabera for delivering 3 cross-functional projects ahead of schedule.
Projects 7Enterprise Angular Migration · Cloud Economics Platform · AI-Powered Code Quality Tool · Enterprise Component Library · Performance Optimization · SRE & DevOps Enterprise Assessment Tool · Azure Monitoring Integration

Projects 7

  • Enterprise Angular Migration

    Angular upgrades across enterprise applications.

    • Led the migration of legacy systems from AngularJS to Angular 15.
    • Upgraded enterprise applications from Angular 13 to Angular 16.
    • Adopted standalone components and signals, cutting bundle size 35%.
    • Wrote migration documentation and an automated test suite, with zero regressions.
  • Cloud Economics Platform

    Real-time cloud resource monitoring and cost optimization.

    • Built D3.js and Highcharts dashboards for real-time VM usage and cost.
    • Added automated cost recommendations that cut cloud spending 30%.
    • Integrated AWS and Azure over REST, polling for real-time resource and cost data.
  • AI-Powered Code Quality Tool

    A VS Code extension that uses the ChatGPT API for automated code review.

    • Raised developer productivity 25%.
    • Built a custom rules engine for code quality checks and suggestions.
    • Generated documentation automatically, cutting manual documentation time 70%.
    • Added a feedback loop that improves suggestion accuracy over time.
  • Enterprise Component Library

    Reusable Angular components that follow W3C accessibility standards and WCAG 2.1.

    • Built 30+ components for forms, tables and data visualization at Collabera, and 40+ at Ascendion, cutting development time 60%.
    • Wrote documentation and usage examples for 20+ team members.
    • Reached 95% code coverage with automated tests.
  • Performance Optimization

    Performance work on enterprise applications.

    • Cut page load times from 23s to 2.5s with lazy loading, pagination and UI improvements.
    • Improved data loading, cutting API response times 75%.
    • Tuned the Angular Material and D3.js implementations.
    • Built a performance monitoring dashboard for real-time metrics.
  • SRE & DevOps Enterprise Assessment Tool

    An Angular assessment tool for Site Reliability and DevOps.

    • Automated monitoring and alerting with Azure Functions.
    • Built real-time dashboards for system health and performance.
    • Automated reports on operational metrics and KPIs.
  • Azure Monitoring Integration

    A web app on an Azure backend with machine-learning workflows.

    • Automated 80% of manual data processes.
    • Synced data in real time between the frontend and Azure services.
    • Built an automated data processing pipeline on Azure Functions.
    • Added error handling and logging with Application Insights.

Stack Angular · TypeScript · JavaScript · Python · Angular Material · D3.js · Highcharts · Storybook · OpenAI · Spring Boot · Microservices · Azure · Azure Functions · Application Insights · CI/CD · DevOps · SRE · W3C

Jan 2021 – Nov 2021 · Cotonou, Benin

LIBS

Jan 2021 – Nov 2021

Software Developer · Cotonou, Benin

Projects 1Warehouse and Sales Management System

Projects 1

  • Warehouse and Sales Management System

    A client-facing platform for inventory, sales and production management.

    • Built real-time inventory tracking with stock-level monitoring across countries.
    • Built sales tracking in multiple currencies and languages.
    • Led the production team of 10+ engineers and delivered on time.
    • Deployed it on Amazon EC2 with added security, across West Africa.

Stack Angular · TypeScript · AWS EC2 · REST APIs · Database Design

Oct 2018 – Dec 2020 · Pune, India

Accenture

Oct 2018 – Dec 2020

Software Engineer · Pune, India

  • Resolved critical ETL validation issues on 5M+ daily records with zero data loss.
  • Built automation scripts that cut manual reporting 70%, from 40 to 12 hours a week.
  • Led production data analysis that had the system switchover ready 3 months early.
Projects 1Barclays - Data Migration & ETL

Projects 1

  • Barclays - Data Migration & ETL

    Data migration and ETL pipelines for Barclays.

    • Built ETL pipelines in Informatica and Ab Initio.
    • Optimized batch processing and data workflows.
    • Added data validation, quality checks and automated monitoring.

Stack Informatica · Ab Initio · Unix · MS-VBA · Python · Node.js · SQL · Oracle DB · NoSQL · ETL · Data Warehousing · Batch Processing · Postman · AWS

May 2018 – Oct 2018 · Pune, India

Enthralltech

May 2018 – Oct 2018

Frontend Developer · Pune, India

Projects 1E-Learning Platform & Chatbot

Projects 1

  • E-Learning Platform & Chatbot

    An e-learning platform with a chatbot for student support.

    • Built platform features in Angular and MongoDB for 10K+ students.
    • Built a chatbot for educational Q&A with .NET and NoSQL that cut support tickets 40% by resolving queries automatically.
    • Implemented IAM for user authentication and integrated AWS for content delivery.

Stack Angular · MongoDB · .NET · AWS · NoSQL · REST APIs

Projects

All projects

dlai-mcp-server

MCP server making DeepLearning.AI's 121-course catalog searchable from Claude Code, Codex, and Cursor. 3 tools: search_courses, get_course_details, list_topics. Published on npm, hosted on Railway.

  • TypeScript
  • MCP
  • Algolia
  • Railway

Blog2Podcast

tech-blog-catchup

Turns engineering blogs from 15 companies into daily AI-narrated podcasts. Ollama Cloud writes a source-grounded summary and a two-speaker script; Kokoro voices it on CPU. Next.js player, FastAPI and SQLite backend.

  • Next.js
  • FastAPI
  • Ollama Cloud
  • Kokoro TTS

pair-programmer-cli

Multiplayer middleware for AI coding agents: two developers share one Claude Code session through a Telegram bot. Pair and solo modes, GitHub issues to claim, driver handoff with a context summary, auto-commit and a pull request at the end.

  • Python
  • aiogram
  • Telegram
  • Claude Code

Email-Link

Find everything in your email using NLP, Knowledge Graphs and Agentic AI

  • Python
  • NLP
  • Knowledge Graphs
  • Agentic AI

Skills

AI

  • LLM applications and agents (Gemini, Claude, OpenAI)
  • LLM evaluation
  • Retrieval and vector search
  • MCP servers
  • Speech (STT, TTS, real-time voice)
DeepLearning.AI
  • LangChain
Bexorg

Engineering

  • Python
  • TypeScript
  • FastAPI
  • React
  • Next.js
  • PostgreSQL
  • Redis
  • Playwright
DeepLearning.AI
  • Neo4j
  • BigQuery
Bexorg

Infrastructure

  • AWS (ECS, RDS, Terraform)
DeepLearning.AI
  • GitHub Actions
Blog2Podcast
  • Azure
Tassel
  • GCP
  • Docker
  • Kubernetes
Bexorg

Contact