Key Responsibilities

• Lead end-to-end Generative AI solutions including data ingestion, vector pipelines, LLM inference, and API development using FastAPI/Flask/Django.
• Architect and implement RAG (Retrieval-Augmented Generation) workflows using vector databases such as Pinecone, Weaviate, PGVector, Supabase.
• Build and optimize prompt engineering frameworks, agent-based orchestration, and fine-tuning of LLMs.
• Integrate and operationalize models from OpenAI, Azure OpenAI, Google Vertex AI, Anthropic, Hugging Face, etc.
• Develop scalable backend systems with strong focus on MLOps: Docker, CI/CD, monitoring, and deployment automation.
• Lead code reviews, enforce engineering best practices, and mentor junior team members.

Must-Have Skills

• 3–8 years of experience in Python development using FastAPI/Flask/Django.
• Hands-on expertise with LLMs / Generative AI: embeddings, RAG pipelines, prompt engineering, fine-tuning.
• Strong knowledge of vector databases: Pinecone, Weaviate, PGVector, Supabase, etc.
• Experience with at least one major cloud: AWS, GCP (Vertex AI preferred), or Azure.
• Solid understanding of software engineering principles: modular architecture, testing, CI/CD, containerization.
• Strong communication, analytical thinking, and problem-solving abilities.

Education & Experience

• Bachelor’s or Master’s in Computer Science, AI/ML, Data Science, or related fields.
• 3–8 years in Python backend/AI engineering roles, with 2+ years dedicated to Generative AI preferred.