Key Responsibilities
- Design and develop AI workflows and production-grade APIs using Python (FastAPI/Flask).
- Lead prompt engineering initiatives and implement RAG (Retrieval-Augmented Generation) architectures and agentic AI patterns.
- Build, deploy, and maintain AI models across all environments (Dev/QA/Prod) with robust monitoring, testing, and documentation.
- Work with data processing pipelines and AI-enabled workflows; implement hybrid prompting techniques and advanced generative AI solutions.
- Leverage GenAI tools and frameworks (LangChain, Hugging Face, LlamaIndex) and explore Gemini LLMs when applicable.
- Collaborate on model deployment and containerization (Docker), version control (Git), and CI/CD practices.
Requirements
- Strong hands-on Python experience.
- Hands-on API development in Python using FastAPI or Flask.
- Experience with data processing and AI-enabled workflows in Python.
- Knowledge of LLM concepts, prompt engineering, RAG, and agentic AI.
- Basic knowledge of hybrid prompting techniques.