🚀 AI/ML Engineer building production-grade GenAI systems, multi-agent architectures, and scalable ML platforms.
💡 Focused on LLMs, RAG systems, and real-world AI products that go beyond demos.

🌐 Portfolio: https://portfolio-3-kappa-rose.vercel.app/

• 💻 2.7+ years of experience (incl. 6 months in AI/ML), transitioned from Full Stack to AI Engineering
• 🤖 Specialized in LLMs, RAG pipelines, and autonomous AI systems
• 🏗️ Building FAANG-level projects with focus on system design, scalability, and performance
• 🔍 Strong interest in AI agents, reasoning systems, and self-improving architectures
• ⚡ Experienced in taking projects from idea → architecture → deployment → optimization

• Advanced RAG with semantic search, document ingestion, and memory
• Optimized retrieval pipelines with embeddings + vector DB
• Backend deployed with FastAPI, scalable architecture

• Autonomous agents for planning, retrieval, and synthesis
• Integrated research pipelines using external APIs (OpenAlex, etc.)
• Focus on reasoning + coordination between agents

• Feedback loops for continuous improvement
• Evaluation pipelines + automated refinement
• Designed like real-world ML systems (not static demos)

Python · PyTorch · TensorFlow · Transformers · LangChain · LlamaIndex
LLMs · RAG · Embeddings · Fine-tuning · Prompt Engineering

FastAPI · Docker · REST APIs · Microservices · PostgreSQL · MongoDB
Vector DBs (FAISS, Pinecone, Chroma)

AWS · CI/CD · Model Deployment · Monitoring · Experiment Tracking

React.js · TypeScript · Streamlit

• 🧠 Production-grade LLM fine-tuning project
• 🤖 Advanced multi-agent AI systems
• ⚡ Scaling GenAI apps for real-world use cases
• 📊 Improving evaluation & benchmarking of LLM systems

• 💼 LinkedIn: https://www.linkedin.com/in/harsh-gupta-b349611ba/
• 📧 Email: harshmail281199@gmail.com

I enjoy turning complex AI ideas into real, working systems — and debugging them until they behave intelligently 😄