Python Gen AI

About the Role

Senior GenAI Platform Engineer

autonomous AI systems

Key Responsibilities

• Architect, implement, and operate

  agentic AI workflows

  using

  LangChain

  and

  LangGraph

  (stateful graphs, event-driven nodes, tool routing, memory, retries, and guardrails).
• Build

  multi-agent systems

  involving agent-to-agent collaboration, hierarchical planners/executors, and tool-augmented reasoning (ReAct, Reflexion, Tree-of-Thoughts, etc.).
• Design reusable

  platform primitives

  prompt and graph registries, tool catalogs, policy/guardrail layers, provider routing, and evaluation harnesses.
• Expose AI agents and workflows via

  versioned APIs/SDKs

  , collaborating with platform teams to establish best practices.
• Integrate and optimize retrieval where required (vector stores, chunking, hybrid search) — focusing on

  agentic solutions

  for complex enterprise tasks.
• Ensure

  production readiness

  — cost and latency optimization, caching, observability, tracing, rate limiting, and incident response.
• Benchmark and fine-tune across

  model providers

  (OpenAI, Anthropic, Azure OpenAI, vLLM/TGI) for reliability, safety, and task success.
• Mentor engineers, lead design/architecture reviews, and contribute to the

  internal GenAI platform roadmap

  .

Must-Have Skills

• 8–12 years

  in software engineering (Python preferred), with

  3+ years

  building LLM-based production applications.
• Deep, hands-on experience with

  LangChain

  and

  LangGraph

  :
• Chains, agents, tools, retrievers, routers, and memory stores.
• State machines, nodes/edges, event streams, retries, checkpointers.
• Tool use (structured tools, code execution, function calling), agent-to-agent communication.

• Strong understanding of

  Agentic AI

  :
• Planning/execution loops (ReAct, Reflexion), self-correction, and tool routing.
• Safety, guardrails, policy enforcement, and PII handling.
• Expertise in

  GenAI platform engineering

  :
• Prompt/graph versioning, A/B testing, provider routing, observability (LangSmith, OpenTelemetry).
• Offline/online evals, hallucination detection, and safety scoring.

• API & Service Delivery:

• Designing REST/gRPC APIs and SDKs for agents and tools with proper authentication and versioning.

• Cloud-Native Deployment:

• Docker/Kubernetes, AWS/GCP/Azure, CI/CD pipelines.
• Strong grounding in

  software engineering best practices

  — testing, profiling, and cost optimization.

Good to Have

• Experience with

  CrewAI, AutoGen, LlamaIndex agents

  , or

  OpenAI Assistants API

  .
• Retrieval technologies —

  Pinecone, Weaviate, FAISS, Milvus, or knowledge graphs

  .
• Model serving experience —

  vLLM, TGI, Ray Serve, Triton

  .
• Observability & eval tools —

  Ragas, DeepEval, G-Eval, Arize, Phoenix, W&B, MLflow

  .
• Knowledge of

  security, compliance, secrets management

  , and tenant isolation.
• Familiarity with

  JavaScript/TypeScript

  for SDK or UI integration.