Description :

- Design, build, and operate production grade agentic and GenAI systems end-to-end. Deliver robust APIs, reusable components, and secure pipelines that connect LLMs with enterprise systems.

- Combine strong software engineering with modern AI practices (RAG, agent orchestration, evaluation) to drive scalable business outcomes.

Key Responsibilities :

Agent & Application Engineering :

- Build multi agent systems (planning, tool use, delegation) using LangGraph or Semantic Kernel.

- Develop REST/gRPC APIs (FastAPI mandatory).

- Integrate tools, SQL, search, and document stores via Model Context Protocol (MCP).

- Connect with model gateways (OpenAI, Azure OpenAI, Bedrock, Vertex AI).

- Deliver pro code solutions (Python focus).

Retrieval, Data & Knowledge :

- Stand up RAG services with embeddings, hybrid/vector search (pgvector, Pinecone, Weaviate, OpenSearch).

- Build ingestion pipelines (Airflow, Prefect, Ray) for diverse enterprise data.

- Optimize retrieval quality with chunking, re rankers, query rewriting.

Quality, Testing & Evaluation :

- Apply evaluation frameworks (Promptfoo, RAGAs).

- Treat prompts/graphs as codeversion, diff, regression test.

- Track AI evaluation metrics for RAG applications.

Security & Compliance :

- Implement red teaming guardrails.

- Enforce policy chains and PII guardrails (OPA/Gatekeeper, Presidio).

Enterprise Integration :

- Ship connectors/events for SAP/CRM/ITSM and Kafka topics.

- Design idempotent, retry safe processors.

Tech Stack & Qualifications :

- Mandatory : Python, FastAPI, LangGraph/Semantic Kernel, one major cloud (Azure/AWS/GCP).

- Preferred : Containerization & Kubernetes (Helm/Argo CD), secondary languages (Java/Go/Node.js).

- Strong engineering mindset with focus on scalability, security, and evaluation.