ML Systems Engineer at MyStage Music · MS in Data Science at UC San Diego
Incoming ML intern at Infoblox for Summer 2026
LinkedIn · Medium · contextjetai.com/nishchay · emailfornishchay@gmail.com
I build production AI systems and the unglamorous infra that keeps them upright. I get nerd-sniped by anything at the intersection of evals, agent orchestration, and inference cost.
Languages Python, SQL, TypeScript, C++, Bash ML & modeling PyTorch, TensorFlow, scikit-learn, XGBoost, CatBoost, Prophet, MLflow LLM tooling LangChain, LangGraph, LlamaIndex, DSPy, MCP, Hugging Face, OpenAI, Anthropic Vector & graph Pinecone, Milvus, Weaviate, FAISS, Neo4j Infra & delivery Docker, Kubernetes, FastAPI, GitHub Actions, Azure, AWS, GCP, Databricks, Supabase Frontend & data viz React, Next.js, Streamlit, Plotly, D3.js, Dash
- Working on the AI pipelines at MyStage Music, a live-music discovery platform connecting independent artists with audiences and venues.
- Shipping fixes and features into the AI tooling I actually use day to day. Recent merges in promptfoo (NVIDIA NIM provider) and dify. Open PRs in garak, dspy, phoenix, the MCP Python and TypeScript SDKs, openllmetry, openai-cookbook, and a few more.
- Reading the LangGraph internals, whatever new agent paper is going viral that week, and the older systems books that age well (Designing Data-Intensive Applications stays open on my desk).
| Project | What it does | Impact |
|---|---|---|
| Knowledge GraphRAG Platform | Entity-linked graph over docs for import/export compliance. LangGraph, vector DB, Salesforce. | +87% answer precision, −45% research time. Auditable citations. |
| Multimodal Synthetic Market Surveys (C5i.ai) | Real-time respondent synthesis for CPG and marketing studies. LangChain, Azure OpenAI, multi-agent, Apify. | ~90% accuracy vs live benchmarks. $300K+ in attributable revenue. |
| AI Sales Development Representative (Wall Street client) | Prospecting, enrichment, personalization, outreach, reply handling for a PE / hedge-fund / family-office target list. LangChain agents, Pydantic workflows, React. | +35% qualified meetings, −60% manual prospecting, 200–300 leads/week. |
| LLM Virtual Try-On Assistant (apparel client) | Diffusion-based try-on (StableVITON) + OpenAI image + LangGraph + MediaPipe + Pinecone RAG over catalog. | Time-on-page +25%, CTR +18%. |
| Predictive Maintenance + RAG (Industry 4.0) | Vibration/temperature anomaly detection + RAG + forecasting for conveyor planners. scikit-learn, Prophet, LangGraph, Databricks. | Unplanned maintenance −15%, planning cycle −30%. |
- Evals are the only thing that scales engineering judgment. Most teams write the eval after deciding the model is good, which is backwards.
- Agent frameworks are mostly thin glue. Read the source before you adopt one.
- The best LangChain users I know also use less of LangChain over time.
- The cheapest performance win is almost always a smaller, better prompt. The second cheapest is caching. Quantization is rarely the answer people think it is.
- REAL MADRID and CR7.
When I get a weekend and a problem statement, I build things like StepWise (AWS Breaking Barriers 2024, digital inclusion copilot), DocuGuard AI (HackAI Dell/NVIDIA 2024, enterprise document risk), and NeuroForecast AI (UCSD SMASH NSF HDR 2026, OOD-robust neural forecasting). Constraints make for sharper systems.
- Revolutionizing Market Surveys through Generative AI for Efficient Data Synthesis, keynote at the Machine Learning Developers Summit 2024, published in Lattice Journal (AoDS), Vol. 5 Issue 1.
- Occasional notes on Medium.