Job Description Role: Agent Engineer
n Experience: 3 - 6 years
n Location: Bengaluru
n Role Summary
n We are building an AI-native B2B intelligence platform. You will build our core Agentic Harness — a performant, configurable agent layer that powers everything from our database search to sourcing and selling agents. This is a hands-on builder role focused on system design, observability, and agent performance.
n Roles & Responsibiliti
n n Build a lightweight, scalable agent harness that allows the business to configure and deploy multiple domain-specific agents.
n Design the core orchestration loop, including memory management, state handling, tool calling, and deterministic guardrails.
n Ensure the agent layer is model-agnostic, easily swappable, and testable across different commercial and open-source LLMs.
n Optimize agent performance for low latency, efficient token usage, and minimal memory footprint.
n Establish robust evaluation frameworks (evals) to measure agent reasoning, tool selection accuracy, and task completion.
n Collaborate with the research team to tune open-source LLMs specifically for optimal agentic behavior and tool use.




n n Skills Required
n Must Have:
n n 3+ years of experience in backend or ML engineering, with strong Python skills.
n Experience building agentic workflows or orchestration loops
n Deep understanding of LLM application architecture, state machines, and API integrations (FastAPI, PostgreSQL).
n Strong systems engineering mindset—you treat agent development as reliable software engineering, not just prompting.
n Experience benchmarking, profiling, and optimizing LLM performance and latency.
n n Valuable to Have:
n n 3+ years of experience in backend or ML engineering, with strong Python skills.
n Experience building agentic workflows or orchestration loops
n Deep understanding of LLM application architecture, state machines, and API integrations (FastAPI, PostgreSQL).
n Strong systems engineering mindset—you treat agent development as reliable software engineering, not just prompting.
n Experience benchmarking, profiling, and optimizing LLM performance and latency.
n

📌 Agent Engineer (Bengaluru)
🏢 Tata Consultancy Services
📍 Bengaluru