AI Engineer / San Francisco

Varun

Menon

I build AI agents, agentic workflows, and context-engineered systems that learn from every human interaction and get smarter in production.

See my work Chat with my AI
01 Work

Legix

Founding AI Engineer / Oct 2024 - Present / San Francisco

$1.6M Pre-Seed

Sole AI engineer. Took the entire AI platform from 0 to 1, now scaling 1 to 10. Built an intelligent bookkeeping system that classifies transactions across hundreds of account categories at 94% production accuracy, up from 58% before my system. Separate modules handle counterparty categorization and transfer matching. The platform learns from every accountant correction, auto-approves high-confidence predictions, and routes edge cases to human review. End-to-end pipeline from bank feed ingestion through agentic classification to automated QuickBooks sync.

Context Engineering Kafka Temporal pgvector Neo4j Pinecone Langfuse TypeScript Python Next.js PostgreSQL

Auto BIM Route

SWE Intern / Jan - May 2024

Built an autonomous meeting bot that joins, records, and transcribes across Teams, Meet, and Zoom simultaneously. 10+ concurrent sessions, 46% compute reduction.

  • Multithreaded architecture with virtual audio cables for simultaneous multi-platform recording
  • NLP speech-to-text pipeline for automatic transcription
Python NLP Multithreading Speech-to-Text

Boson Motors

AI Engineer Intern / Jun - Aug 2023

Predictive maintenance on sensor data. Reduced downtime by 28% and extended vehicle life by 19%. Built OpenCV path-finding for autonomous agricultural navigation.

  • Sensor fusion models on Light Utility Vehicle telemetry data
  • Real-time obstacle detection for trees, animals, people in unstructured terrain
PyTorch OpenCV Sensor Fusion

HashedIn by Deloitte

SWE Intern / Jan - May 2022

Full-stack on production client products. React/Redux frontends, Node.js/GraphQL backends, DynamoDB storage layer.

  • Client-facing React/Redux apps integrated with GraphQL + Express backends
  • DynamoDB connection layer for scalable cross-service storage
React Node.js GraphQL DynamoDB

Saaragh Technologies

ML Engineer Intern / Jul - Sep 2021

Cancer detection models under 100MB with clinical-grade precision. Warehouse CV tracking on GCP, shipped in under a week.

  • Lung and colon cancer detection models optimized for size and accuracy
  • OpenCV + FFmpeg warehouse tracking for forklift, box, and rust detection
PyTorch OpenCV Flask GCP

Dayananda Sagar University

Research Assistant / Aug 2020 - Jan 2022

Bone age prediction from radiographs using depth-wise separable convolutions. Published at IEEE ICSES 2021.

Deep Learning CNNs Medical Imaging
02 Projects
Tic-Tac-Toe-Two

Tic-Tac-Toe-Two

Your 3rd move deletes your 1st. The game never draws. Real-time multiplayer over Socket.IO with private rooms and Bo3/Bo5 series.

Vue 3 Socket.IO Express Docker
AI Water Gun

AI Posture Water Gun

Detects slouching via MediaPipe and fires a water gun at you. Servo tracks your face for aiming. Arduino serial control.

MediaPipe OpenCV Arduino
Mem0 ChatBot

Mem0 ChatBot

Chatbot that remembers across sessions. No chat history sent to the LLM. All continuity comes from Mem0's semantic memory layer.

Next.js GPT-4o Mem0 TypeScript
AI Learns Snake

AI Learns Snake

Deep Q-Network learns Snake from scratch. Custom Pygame engine, 11-state representation, experience replay. Zero human strategy.

PyTorch DQN Pygame
Emotion Music

Emotion Music Rec

Webcam reads your expression, CNN classifies mood, K-Means clusters Spotify tracks by audio features. Serves matching songs.

Keras OpenCV Spotify API
ArtMovr

ArtMovr

Knowledge graph over 610K MoMA + Met records. SPARQL queries on RDF triples in Stardog Cloud. No ORM, pure graph queries.

Django SPARQL RDF/OWL Stardog
Fire Detection

Fire Detection API

YOLOv8 Large exported to ONNX with hand-rolled NMS in pure NumPy. FastAPI serving, 0.885 mAP@50, fully Dockerized.

YOLOv8 ONNX FastAPI Docker
Quote Analysis

Quote Analysis

Benchmarking 8 embedding models (MiniLM, MPNet, E5, Instructor-XL) on cosine similarity search. Systematic model selection study.

Sentence-Transformers PyTorch scikit-learn
View all on GitHub

Drag to explore

03 About
Varun and Yuzu
San Francisco, CA

AI engineer in San Francisco. I build production AI systems: multi-agent architectures, agentic workflows, context engineering, and self-improving pipelines that learn from human feedback at every step.

At Legix, I designed the entire AI platform as the sole engineer, from classification engines to evaluation frameworks to observability stacks. Before that, I shipped CV models for cancer detection, built autonomous meeting bots, trained RL agents from scratch, and wrote path-finding for autonomous vehicles. I care about AI that works in the real world.

Focus

AI Agents Context Engineering Agentic Workflows MCP GraphRAG

Education

  • MS Software Engineering, ASU (3.8)
  • BTech Computer Science, DSU (8.9)

Publication

IEEE ICSES 2021 / Bone Age Assessment

Certifications

  • AWS Certified Cloud Practitioner
  • OCI Generative AI Professional

Stack

Python TypeScript PyTorch React Next.js PostgreSQL Docker AWS GCP
04 Contact

Let's connect

Always interested in challenging problems and new opportunities.

Say hello Book a call