AI/ML Engineer | LLMs • RAG • FastAPI • Production Systems
Open to offersNew to PlatformI build production AI/ML systems—RAG pipelines, LLM integrations, semantic caching that cuts costs 60%.
Recently deployed a Financial Document Analyzer using FAISS, multi-provider LLM routing (Groq/Gemini/OpenAI), and FastAPI. Maintains 95% accuracy while reducing API costs by 60%.
I debug by reading traces, own features end-to-end, and ship fast. Looking for roles where I can contribute immediately while pushing myself harder.
Stack: Python, FastAPI, PyTorch, TensorFlow, LangChain, FAISS, PostgreSQL, Docker
GitHub: github.com/naeemkhan988
LinkedIn: linkedin.com/in/naeem-khan988
Open to: AI/ML Engineer, Junior/Associate roles. Remote-friendly or on-site anywhere in Pakistan. Available to start immediately.