Experience Required:

- 6+ years in AI/ML, data science, or software engineering.

- 3+ years in GenAI, LLM, RAG, conversational AI, or ML productionisation.

Key Responsibilities :

- Build and deploy secure, production-grade AI agents using GenAI frameworks.

- Develop APIs with Python (FastAPI, Flask, or similar).

- Implement RAG architecture: ingestion, chunking, embeddings, retrieval, ranking, grounding, citations, evaluation.

- Apply LLM techniques: embeddings, vector search, prompt design, evaluation, hallucination control.

- Manage MLOps/LLMOps: deployment, monitoring, evaluation, versioning, observability.

- Ensure security and governance: IAM, PII handling, prompt injection risks, data leakage prevention, approval workflows.

- Deliver working prototypes and production-ready services.

Must-Have Skills :

- Python, FastAPI, REST APIs, async processing.

- LLM application development and RAG implementation with vector databases.

- Prompt engineering, tool/function calling, structured outputs.

- LLM security: prompt injection, guardrails, access control.

- GCP Vertex AI, Gemini, Cloud Run, GKE, or equivalent.

- Agent orchestration using ADK, LangChain, LlamaIndex, Semantic Kernel, CrewAI, AutoGen, or similar.

- Evaluation frameworks: Vertex AI, Evals, RAGAS, regression tests.

Nice to Have :

- Google Agent Development Kit (ADK).

- Gemini Enterprise Agent Platform.

- Agent observability and tracing.

- Multi-agent architecture.

- Human-in-the-loop approval flows.

- Enterprise knowledge graph / search integration.