who I am
ABOUT4+
yrs exp
6+
companies
10+
shipped
Founding Engineer building LLM-driven systems that work for real users.
Based in San Jose, CA. I've spent the last 4+ years building production systems across fintech, EdTech, and AI: from compliance platforms at Deloitte to multimodal RAG at Astranetix and agentic evaluation pipelines at SJSU.
I care deeply about systems that are observable, maintainable, and actually solve real problems, not just impressive demos. My stack is Python-first, cloud-native, and increasingly agent-driven.
Published research on Hindi NLP. Outside engineering: basketball, sketching, and building things with my hands.
education
M.S. Software Engineering
San Jose State University
2023 – 2025 · GPA 3.6
B.E. Engineering
Osmania University, Hyderabad
2016 – 2020 · GPA 3.5
things I've built
PROJECTS
Multi-agent evaluation system using CrewAI where agents autonomously decompose rubrics, retrieve context via Weaviate vector search, and score submissions using Gemini on GCP. Multimodal RAG over text and image inputs reduced manual grading effort by 60%.
Free, open-source Android client for LM Studio. Stream chat from models on your Mac or PC over Wi‑Fi, or run GGUF models on-device via llama.cpp. Expo + React Native app with local model library, LAN discovery, and streaming chat UI.
Text-to-image sketch generation using Stable Diffusion + ControlNet for shape and style consistency. End-to-end full-stack with async job handling and serverless image processing on AWS. 45% latency reduction via embedding caching and request batching.
Production RAG combining text and document embeddings. Weaviate + GraphQL retrieval, tuned HNSW parameters. Scalable inference on AWS Lambda and S3.
Knowledge graph-powered RAG using LangChain and Neo4j. Hybrid search combining vector similarity and graph traversal for richer LLM responses.
Full-stack booking platform with React, Node.js, and GraphQL for real-time seat selection. Microservice backend with MongoDB, containerized via Docker, deployed with CI/CD.
Flutter mobile app scanning ID documents and tracking expiry dates. OCR-based extraction, push notifications, offline-first, cross-platform iOS & Android.
what I work with
SKILLSLanguages
AI / ML
Frameworks
Databases
Cloud & DevOps
Data
where I've worked
EXPERIENCE
research
PUBLICATIONInternational Journal of Innovative Engineering Research and Technology (IJIERT) · 2020
Proposed a machine learning approach for sentiment classification of Hindi-language text using a Naive Bayes classifier, addressing the unique morphological and syntactic challenges of Hindi NLP.
let's talk
CONTACTget in touch
Based in San Jose, open to remote. Hiring for AI engineering, full-stack, or founding roles — or just want to talk shop on agents, RAG, and what you're building.
Usually replies within 48 hours
