Source description
About the role
Key Responsibilities
Develop and deploy AI agents using Python and modern agentic frameworks such as LangChain, AutoGen, CrewAI, Haystack, or custom-built solutions.
Design and implement A2A (Agent-to-Agent) workflows, enabling agents to collaborate, reason, negotiate, and complete end-to-end tasks autonomously.
Fine-tune, evaluate, and integrate Large Language Models (LLMs) including OpenAI, Anthropic, Llama, Mistral, and other foundation models.
Build and manage retrieval-augmented systems using vector databases, knowledge graphs, embeddings, and long-term memory mechanisms.
Develop scalable backend services to support AI workloads using FastAPI, Flask, Docker, and cloud platforms (AWS/GCP/Azure).
Integrate external tools and capabilities such as APIs, databases, workflow engines, and custom toolchains for agent skills.
Optimize model inference for performance, latency, throughput, and cost efficiency across different deployment environments.
Collaborate closely with product, engineering, and research teams to bring agentic AI features from ideation through development and production deployment.
More at EXL