Overview :

We are seeking a seasoned Team Lead - Agentic Systems to guide and mentor an engineering team in building, scaling, and productionizing enterprise-grade autonomous AI applications, AI Agents, and AI Automations.

In this role, you will combine hands-on technical expertise in LLM orchestration, RAG pipelines, and agentic workflows with team leadership - driving best practices, system reliability, and architectural standards across multi-agent enterprise deployments.

You will translate business vision into production AI systems while fostering team growth and continuous technical improvement.

Work Details :

- Work Mode : Hybrid

- Work Location : Bangalore

- Experience : 7 - 10 yrs

Key Responsibilities :

- Lead, mentor, and grow a team of AI and software engineers; perform regular code reviews, manage sprint execution, and drive career development and hiring.

- Own the end-to-end architecture, delivery, and operational reliability of production-grade, autonomous AI agents, multi-agent teams, and workflow automations.

- Work with ARB to establish standards and design patterns for LLM orchestration (LangChain, LangGraph, etc.), tool/API integration, state management, and multi-step reasoning systems.

- Define and implement continuous evaluation harnesses and production observability.

- Implement enterprise-grade guardrails, access control boundaries, prompt injection defense, and governance across multi-tool, multi-agent systems.

- Lead the engineering of advanced Retrieval-Augmented Generation (RAG) pipelines, integrating vector databases, hybrid search, and structured/unstructured enterprise data stores.

- Build and maintain agent integrations with enterprise applications across multiple business use cases, via REST APIs, connector frameworks, or MCP-style tool registries.

- Operate within existing access-control, logging, and audit patterns for multi-tool agent systems; flag gaps to the architecture team rather than redesigning independently.

- Collaborate closely with Product, Security, Enterprise Architecture, and Infrastructure teams to align agentic capabilities with strategic business use cases.

Required Skills :

- 7 years of professional software engineering experience, including at least 1 - 2 years of hands-on building with LLMs or agentic frameworks.

- 1+ years of experience in direct team leadership, technical mentorship, or managing small-to-medium-sized engineering teams.

- Strong proficiency in Python and/or Node.js for AI and backend development.

- Working knowledge of major LLM providers (e.g., OpenAI, Anthropic) and prompt orchestration frameworks (LangChain, LangGraph).

- Hands-on expertise in building LLM applications, including prompt engineering, tool integration, RAG, multi-agent workflows, and context management.

- Experience integrating external tools/APIs and enterprise SaaS applications via REST APIs or connector frameworks.

- Working knowledge of SQL and NoSQL databases.

- Experience writing test cases/evaluation harnesses for agent/LLM behavior (accuracy, hallucination, tool-call correctness).

- Familiarity with agent evaluation techniques (LLM-as-a-judge, benchmark design, automated regression testing).

- Understanding of access-control, audit-logging patterns, AI security, prompt injection, data leakage, and guardrails.

- Strong debugging skills and the ability to implement complex multi-step systems.

Nice to Have Skills :

- Understanding of cloud deployment and infrastructure (AWS, GCP).

- Knowledge of containerization and CI/CD pipelines (Docker, GitHub Actions).

- Experience with AI observability, guardrails, and safety mechanisms for LLMs.

- Familiarity with data warehouses or analytical query engines for large-scale structured retrieval.

- Background in enterprise SaaS integration patterns and multi-tenant system design.