RAG (FAISS, BM25) • LangChain • LangSmith • Ragas • OpenAI • Whisper • LLM Evaluation • Prompt Engineering
🔹 Build scalable Playwright automation frameworks
🔹 Design end-to-end testing for AI & LLM systems
🔹 Validate RAG pipelines and reduce hallucinations
🔹 Automate voice & chat AI workflows (STT + LLM + TTS)
🔹 Create AI evaluation frameworks using LLM-as-a-Judge