Responsibilities
- Build production-ready AI applications using Python and FastAPI.
- Design LLM pipelines including data ingestion, inference, and response generation.
- Leverage GCP tools like Vertex AI, Cloud Run/Functions, BigQuery, and Cloud Storage.
- Apply advanced prompt engineering techniques to enhance LLM outputs.
- Implement vector stores and embeddings for semantic search and RAG.
- Use orchestration frameworks (e.g., LangChain, LangGraph, CrewAI) for complex workflows.
- Integrate AI systems with enterprise platforms and maintain robust data flows.
- Follow best practices in coding, testing, and deployment within CI/CD pipelines.
- Continuously explore and recommend emerging tools and AI technologies.