AI Engineering Lead

Overview

Lead the AI & Automation team in building and operating Flutter's enterprise AI assistant and agent platforms. This hands-on technical leadership role combines AI engineering, architecture, people leadership and cross-functional teamwork.

What you'll do

• Set the technical direction for enterprise AI assistant and agent platforms, making architectural decisions across LLM inference, agentic frameworks, context engineering, guardrails and system design.
• Own the selection, deployment and optimisation of LLM inference systems, including AWS Bedrock and LiteLLM, focusing on model routing, cost, latency and operational excellence.
• Design production-grade context pipelines, RAG systems and prompt architectures, establishing patterns, standards and evaluation practices.
• Guide decisions around token economics, context limits, latency budgets and capability-to-cost trade-offs.
• Establish guardrails, security and Responsible AI practices addressing prompt injection, data leakage, authentication, access control and sensitive data handling.
• Choose technologies across agentic frameworks such as LangChain, LangGraph, Strands and ADK, and establish scalable orchestration and tool-use patterns.
• Own problems end-to-end, from LLM integration and backend services through user-facing interfaces, APIs and integrations using AWS services, MCP and modern engineering standards.
• Build, lead and mentor a pod of 2–3 AI developers, supporting their technical and career growth.
• Establish engineering standards through code reviews, architectural guidance and continuous technical development.
• Lead the team through production incidents, complex technical challenges and post-mortems, driving systemic improvements.
• Develop a culture of learning, experimentation, psychological safety and continuous improvement, while encouraging calculated technical risks.
• Partner with product managers and business stakeholders to translate requirements into scalable technical solutions and prioritise high-impact work.
• Collaborate with data scientists and platform engineering teams to integrate AI solutions into existing infrastructure.
• Communicate complex AI concepts to technical and non-technical audiences, present architectural decisions to leadership and influence technical direction across teams.

What you'll need

• Bachelor's degree in Computer Science, AI or a related STEM field.
• 8–12 years of software development experience, including 2–3+ years focused on AI/ML or agentic systems development.
• Experience leading or mentoring technical teams, with the ability to establish technical direction and drive delivery through others.
• Advanced Python and backend engineering skills, including production experience with FastAPI, Flask and async patterns.
• Hands-on expertise with AWS Bedrock, LiteLLM or similar LLM inference platforms, including model routing, API design, cost optimisation and production deployment.
• Strong experience in context engineering, RAG and prompt architecture, and ability to evaluate trade-offs and design production-grade solutions.
• Deep experience with 2–3+ agentic frameworks, such as LangChain, LangGraph, Strands, ADK or CrewAI, including orchestration, tool use and multi-agent patterns.
• Experience designing and implementing guardrails, content filtering and Responsible AI practices in production environments.
• Strong AI security fundamentals, including prompt injection, data exfiltration, model misuse, OAuth, JWT and least-privilege design.
• Proficiency with AI coding tools such as Claude Code, GitHub Copilot or OpenCode, and ability to validate AI-generated code and guide others in their use.
• Expert knowledge of software engineering fundamentals, including SDLC, Git, API design, system architecture and collaborative engineering.
• Exceptional communication and influencing skills, including the ability to explain complex technical concepts to technical and non-technical audiences and build consensus without relying on formal authority.

Nice to have

• Full-stack experience across React, TypeScript, backend services and AI integration.
• Hands-on experience designing and operating production RAG systems and vector databases, including Pinecone, pgvector, OpenSearch or Weaviate.
• Experience with Model Context Protocol (MCP) and its implementation in AI agent systems.
• Contributions to AI/ML or agentic open-source frameworks such as LangChain or CrewAI.
• Experience in gaming, sports betting, financial services or other heavily regulated environments.
• A track record of growing engineers, building high-performing teams or leading technical initiatives that delivered material business impact.
• Demonstrated curiosity and thought leadership in AI, with an appetite for emerging technologies and the ability to form and defend informed technology choices.

Details

• Location: Hyderabad, India.
• Hybrid model with 2 office days per week.