· Expert-level Python development skills,
with hands-on experience in at least one web framework such as FastAPI, Django,
or Flask.
· Proficient in asynchronous programming in Python, with a strong
understanding of event loops, concurrency, and async design patterns.
· Practical experience and understanding of Retrieval-Augmented
Generation (RAG), embedding models, and text chunking techniques.
· Demonstrated expertise in prompt engineering, including crafting
effective prompts for LLMs and optimizing prompt performance.
· Familiarity with integrating LLMs using APIs (e.g., OpenAI,
Anthropic, Hugging Face, Azure Open AI, AWS Bedrock) in production-grade
systems.
· Experience with Vector Databases (e.g., Pinecone, FAISS, Chroma,
or Qdrant)
· Familiarity with LangChain, LlamaIndex, or similar GenAI
orchestration frameworks.