AI Engineer

JD:

• Embed with client domain teams to identify high-value AI opportunities, map pain points to platform capabilities, and validate feasibility before solutioning.


• Design, build, and deploy AI agents using agentic frameworks (LangGraph, CrewAI, Google ADK) with tool use, memory, structured outputs, and error recovery.


• Build retrieval-augmented generation (RAG) pipelines grounded in client enterprise data — designing context engineering and memory architectures for multi-turn and multi-agent workflows.


• Integrate AI solutions with client enterprise systems via APIs, MCP tool gateways, CRM, billing, and operational platforms — handling authentication, rate limiting, and production-grade error handling.


• Define success metrics in partnership with client stakeholders, build evaluation harnesses, and establish continuous benchmarking and quality monitoring for deployed AI systems.


• Serve as a trusted technical partner to client teams — run workshops, pair-program with domain engineers, and drive AI adoption and enablement on the ground.


• Surface platform gaps, friction, and feature requests back to Cognizant's AI architecture and engineering teams to improve reusable offerings.

Must Have's:

• 3-5 yrs experience


• Master’s degree in Computer Science, Artificial Intelligence, Data Science, or a related field with 1–3 years of relevant experience. PhD preferred.


• Strong production-grade Python programming skills — not notebook-grade; experience building deployable, maintainable AI applications.


• Hands‑on experience with LLMs (GPT, Claude, Gemini), prompt engineering, structured outputs, function calling, and agentic workflow design.


• Experience designing and deploying RAG pipelines — embeddings, vector databases, reranking, hybrid search, and retrieval optimization.


• Familiarity with agentic AI frameworks such as LangGraph, LangChain, CrewAI, Google ADK, or similar orchestration tools.


• Working knowledge of REST APIs, cloud platforms (AWS, Azure, or GCP), Git, Docker, and modern software development practices.


• Strong analytical, problem‑solving, and communication skills with the ability to explain AI trade-offs to non-technical stakeholders.


• Consultative mindset — comfortable operating in ambiguous environments, discovering problems, and defining approaches independently.