Gen AI Engineer (LLM Integration) - CONTRACT

We are looking for a talented AI Engineer to join our client

Location : Hybrid – Bangalore, Cessna Business Park

Type : Ongoing Contract – Long Term

Role Responsibilities :

Design, build, and maintain generative AI workflows and agent systems using Python

Develop and deploy containerized microservices on cloud platforms (AWS, GCP, Azure)

Integrate with LLMs via APIs (OpenAI, Claude, Gemini) and implement prompt engineering best practices

Build and support agent orchestration tools (LangChain, ReAct, CrewAI, or similar)

Manage data flow through vector stores (ChromaDB, Pinecone) and support RAG pipelines

Implement and manage API proxies, session handling, and authentication (JWT)

Set up observability tools (logging, tracing, monitoring) for AI workflows and agents

Collaborate asynchronously with cross-functional teams and document architecture decisions

Prototype quickly and iterate using metrics, logs, and user feedback

Apply security best practices to LLM integration

Required Skills & Experience :

3–5+ years of Python development, including async and modular design patterns

Hands-on experience with container tools (Docker / Podman) and cloud deployments

Familiarity with API design, FastAPI, REST, and WebSocket integration

Experience with at least one LLM orchestration / agent framework (LangChain, AutoGen, OpenAgents)

Strong understanding of prompt / response logging, token usage, and cost tracking

Proficiency with version control (Git) and CI / CD workflows

Excellent written communication and comfort working in distributed teams

Nice-to-Have :

Experience with OpenTelemetry, LangSmith, or LLM eval frameworks

Familiarity with security concerns in GenAI environments

Prior work integrating enterprise systems or external APIs

Background in NLP, ML, or cognitive architectures

If you are passionate about AI, LLMs, and building next-gen intelligent systems , this is an exciting opportunity!