Role & responsibilities
- Design and develop robust Python applications and APIs for AI/LLM-based services.
- Fine-tune, evaluate, and deploy LLMs using frameworks like Hugging Face Transformers, LangChain, or OpenAI APIs.
- Build and optimize pipelines for prompt engineering, retrieval-augmented generation (RAG), and model inference.
- Collaborate with cross-functional teams to integrate LLMs into real-world applications (e.g., chatbots, summarization tools, code generation).
- Implement scalable backend systems using FastAPI, Flask, or Django.