Harshit B.

I help startups and companies build production-ready AI systems powered by LLMs, RAG, AI Agents, NLP, and scalable backend engineering. I hold a Master’s degree in Data Science from New York University and have worked with organizations like Amazon, IBM Research, Arcus Biosciences, HackerRank, and Zeta on large-scale AI/ML and software engineering systems. I’ve also worked with and delivered training/technical solutions for clients and platforms including GeeksforGeeks, upGrad, and HackerRank in areas spanning Generative AI, software engineering, data science, DSA, and AI-powered systems. Over the past few years, I’ve built: ✅ RAG pipelines for enterprise-scale knowledge systems ✅ AI Agents with multi-agent orchestration and reasoning ✅ Semantic search systems over millions of documents ✅ LLM fine-tuning pipelines using LoRA/QLoRA ✅ Recommendation systems and retrieval architectures ✅ Scalable ETL + ML pipelines with Spark, Kafka, and AWS ✅ Full-stack AI applications with modern backend infrastructure ✅ Production-grade vector search systems using FAISS/Chroma ✅ NLP systems for biomedical, legal, and enterprise domains Some highlights of my work include: • Built AI-powered semantic search across 10M+ biomedical records • Reduced LLM query latency from 2.6s → 0.7s using quantization + optimization • Designed 20+ production RAG systems using LangChain, LlamaIndex, OpenAI, Gemini, and vector databases • Processed 10M+ monthly transactions in distributed ML systems • Developed autonomous multi-agent systems for industrial AI workflows • Won 1st place at the NVIDIA + Dell Technologies Hackathon at NYU for building a privacy-first Edge AI healthcare system Tech Stack: Python, PyTorch, LangChain, LlamaIndex, OpenAI APIs, Gemini, FAISS, ChromaDB, AWS, Docker, Kubernetes, Spark, Kafka, SQL, FastAPI, REST APIs, Vector Databases, MLOps, Hugging Face, NLP, Deep Learning, RAG, AI Agents, Recommendation Systems What clients usually hire me for: 🔹 AI Chatbots & AI Assistants 🔹 RAG Pipelines 🔹 AI Agent Development 🔹 LLM Fine-Tuning 🔹 Semantic Search Systems 🔹 Full-Stack AI Applications 🔹 ML/AI Backend Engineering 🔹 Data Science & NLP Solutions 🔹 AI Prototyping for Startups I focus on building systems that are not just impressive demos, but scalable, production-ready, optimized, and actually useful in real-world environments. If you're building something in AI, GenAI, NLP, intelligent automation, or scalable software systems — I’d love to help bring it to production.