harshit = {
"role" : "AI Systems Engineer | Applied AI / Agentic Systems",
"focus" : ["Agentic AI", "Multi-agent Orchestration", "AI Evaluation", "On-device ML"],
"building" : ["AIOS — local-first, offline AI runtime"],
"researching" : ["PTF — Agentic AI Failure Study (SSRN)", "Genesis Lock — Blockchain AI Governance"],
"philosophy" : "From math to production. No API wrappers, no shortcuts.",
"location" : "India 🇮🇳 — India-first deployment, always.",
}|
📄 PTF — Protection Toward Future Empirical study of an agentic AI failure incident An investigation into a real multi-agent system failure — root cause analysis, failure cascade mapping, and safety mitigations. Submitted to SSRN. 🔗 papers.ssrn.com/sol3/papers.cfm?abstract_id=6472278
|
| Project | What | Status |
|---|---|---|
| 🖥️ AIOS | Local-first, offline AI desktop assistant + AI-native operating environment — zero cloud dependency | ✅ Live |
| Project | Signal | |
|---|---|---|
| ⚡ | Anthropic Performance Challenge | 10.2× kernel speedup on Anthropic's real hiring take-home — VLIW cycles: 147K → 14K |
| 🧠 | micrograd-JAX | Rebuilt Karpathy's autograd engine in JAX — grad, jit, vmap, XLA-compiled, GPU-ready |
| 🖥️ | AIOS | Local AI desktop assistant, Ollama-powered — built before on-device AI was a trend |
| 📚 | ML Fundamentals | 19 notebooks — every core ML algorithm from scratch in NumPy (#100DaysOfML) |
| 🏭 | CodeAlpha ML Internship | Production ML pipelines: credit scoring, CNN character recognition, disease prediction, speech emotion recognition |
Languages
AI / ML
Tools & Infra
I'm actively looking for ML Engineer / Applied AI / AI Systems roles — remote globally or India-based.
If you're building in agentic AI, multilingual NLP, on-device inference, or AI safety — let's talk.
"Build from first principles. Ship to production. Leave the APIs for later."