Mukund Ojha
AI Engineer. I build AI agents that survive production. I build them for real customers, then deploy them myself.
Email: muojha@ucsc.edu |
LinkedIn |
GitHub |
GradeRight.org |
Download résumé (PDF)
Experience
Lead App Engineer, TopTutors (May 2026 to Present)
- Deploy and iterate AI features inside a customer's environment as the only engineer, from pilot through production across 100+ zero downtime releases.
- Built an LLM pipeline that ingests chunked PDFs, extracts questions, and autogrades submissions, cutting assessment digitization from hours to minutes.
- Work directly with nontechnical school stakeholders to turn operational problems into features, then defend the technical tradeoffs back to them.
- Own the full stack and the AWS infrastructure under it, Next.js and React on the front, Python and TypeScript services on PostgreSQL behind it.
Founder and Software Engineer, GradeRight.org (September 2025 to Present)
- Built and run a production AI grading platform serving 30,000+ users as founder and sole engineer.
- Designed the agent pipeline behind it, a relevance gate, parallel grading passes against a structured rubric, and median aggregation that removes run to run drift.
- Built the evaluation harness that gates every release, golden sets and automated accuracy checks, with instructor override held under 10% as ground truth.
- Cut serving cost by routing light gating work to a small model and self hosting the heavy path on vLLM.
Assistant Manager, Machine Learning Engineer, Avaada Energy (October 2023 to September 2025)
- Built and deployed ML services into 32+ live industrial sites, working on the ground with field engineers, saving $50K+ annually.
- Engineered Spark ETL pipelines over fleet telemetry and built the anomaly detection and forecasting models on top of them.
- Deployed containerized services on Docker and Kubernetes across AWS and Azure, with monitoring, alerting, and on call recovery.
Projects
- Multiagent Orchestration Framework. Planner, Worker, and Reviewer agents invoking tools through one typed shared state, with a guard node validating every update before it commits and semantic checkpointing that rolls the system back. Cut token usage 62% while raising HotpotQA accuracy from 50% to 54%.
- RAG Based Legal AI Agent. Multihop RAG over a 5,000+ document corpus, hybrid BM25 and dense retrieval, cross encoder reranking over FAISS and Qdrant. Improved recall 22% and cut research time 40%.
- AI Real Estate Agent. Multi agent system for property research, pricing analysis, and recommendation generation, at sub 60 second end to end latency.
- CaseLumen. Agentic RAG for legal professionals, designed after surveying practicing Indian lawyers around what they distrusted about AI.
- SlugMarket. A student marketplace designed, built, and launched live on the App Store, with row level security, verified campus sign in, and real time chat.
Research
- Commit Before Trust: Transactional Shared Memory for Multi-Agent LLMs (Under Review, 2026). Mukund Ojha, Sakshi Konnur, Saranya Kolachana, UC Santa Cruz. 62% fewer tokens, HotpotQA 50% to 54%.
- Diagnosing How Frontier LLMs Fail at Lean: A miniF2F-v2 Evaluation Study (Under Review, 2026). Mukund Ojha, sole author, UC Santa Cruz.
- RAG Robots: Retrieval-Augmented Generation for Enhanced Robotic Task Planning (Preprint, 2026).
- Two Stage Residual Models for Robust Cloud Ramp Prediction (Preprint, 2025).
Expertise
AI agents and orchestration (LangGraph, CrewAI, AutoGen, tool calling, checkpoint and rollback). Agent evaluation and reliability (golden set regression harnesses, LLM as judge, RAGAS, human in the loop review). LLM systems in production (LLM APIs, prompt engineering, vLLM serving, model routing, prompt injection hardening). Retrieval and RAG (FAISS, Qdrant, ChromaDB, hybrid BM25 and dense search, cross encoder reranking). Forward deployed delivery (scoping with nontechnical stakeholders, pilot through production rollout, incident response). Backend, data, and infrastructure (Python, TypeScript, FastAPI, React, PostgreSQL, Spark, PyTorch, Docker, Kubernetes, AWS, Azure, CI/CD).
Education
M.S. in Computer Science and Engineering, University of California Santa Cruz, GPA 3.92/4.00, graduating December 2026. B.Tech in Computer Science Engineering, Chitkara University, GPA 4.0/4.0.