About the Role
(Remote | Full-time | ₹28L – ₹55L/year)
We're building AI systems that don't just respond — they reason, plan, and act. As Engineering Manager for AI & Agentic Systems, you'll lead a team of engineers building agentic applications powered by modern LLMs, multi-agent orchestration networks, and MCP (Model Context Protocol) integrations that connect AI to real-world tools and data. You'll balance hands-on technical leadership with people management — setting technical direction, unblocking your team, and ensuring what ships is production-grade, reliable, and scalable. If you love building intelligent systems and growing the engineers who build them, this role is for you.
What You'll Do
Technical Leadership
- Set the architectural direction for agentic AI systems — multi-step reasoning pipelines, autonomous task agents, and tool-using LLM workflows using frameworks like LangGraph, AutoGen, or CrewAI
- Guide the design and maintenance of MCP (Model Context Protocol) servers and clients connecting LLMs to internal tools, APIs, databases, and external services
- Oversee RAG pipelines and vector search infrastructure (pgvector, Pinecone, Weaviate) to ensure AI responses are grounded, accurate, and cost-efficient
- Drive technical decisions on foundation model selection and integration (Anthropic Claude, OpenAI, Gemini, and open-source models like Llama and Mistral)
- Lead root-cause investigations for complex AI production issues — prompt failures, agent loops, latency, and cost regressions
- Review architecture and code for scalable web and backend systems built on React.js, Node.js, Python, and serverless AWS Lambda workloads
People & Team Management
- Hire, mentor, and grow a team of engineers working on agentic AI and full-stack systems
- Run design reviews, pair programming sessions, and 1:1s to raise the bar on code quality and technical judgment
- Own sprint planning, prioritization, and delivery timelines in partnership with product stakeholders
- Foster a culture of experimentation and rigor — balancing fast iteration on AI systems with production reliability
- Represent the team's technical roadmap to senior leadership and cross-functional partners
What You Bring
- 5+ years of hands-on software engineering experience, including 1–2+ years in a technical leadership or people management role
- Strong hands-on background with React.js, Node.js, and/or Python
- Experience building with LLM APIs and prompt engineering (tool calling, structured outputs)
- Proven experience deploying and scaling serverless workloads on AWS Lambda
- AWS Certification (Solutions Architect, Developer, or equivalent)
- Deep understanding of agentic AI concepts — planning loops, memory, tool use, and multi-agent coordination
- Track record of mentoring engineers and driving technical decisions across a team
- Bachelor's degree or equivalent in Computer Science or related field
Bonus Points
- Direct experience building or consuming MCP servers
- Hands-on with LangChain, LangGraph, AutoGen, or CrewAI
- Familiarity with RAG architectures and vector databases
- Experience with AI observability tools (LangSmith, Arize, Helicone)
- Experience with open-source model hosting (Ollama, vLLM, HuggingFace)
- Prior experience managing a distributed/remote engineering team
Skills: MCP · Agentic AI · LangGraph · RAG · LLM APIs · Prompt Engineering · React.js · Node.js · Python · AWS Lambda · Vector Databases · Serverless · Engineering Management · Technical Leadership
