Technical Lead - Gen AI

About Role :

We are looking for a Technical Lead to own the architecture and delivery of client-facing Generative AI applications. You will lead a team of 35 engineers, translate business requirements into technical solutions, and serve as the primary technical point of contact for clients.

The role combines technical decision-making, team leadership, and client engagement. You will guide both existing projects and new engagements from discovery through production. The emphasis is on architecture, technical oversight, and delivery ownership, with occasional code reviews and involvement in complex technical issues.

Key responsibilities:

• Own solution architecture for GenAI applications, including retrieval-augmented generation (RAG), agent workflows, and integration with enterprise systems and APIs.
• Work with clients to clarify requirements, define acceptance criteria, and translate business needs into feasible delivery plans.
• Make and communicate technical trade-offs across solution quality, reliability, security, latency, cost, and maintainability.
• Lead a team of 3–5 engineers: break down work, set priorities, manage dependencies, remove blockers, and maintain delivery quality.
• Own project scope, estimates, timelines, and delivery risks. Communicate changes and negotiate priorities with clients and internal stakeholders.
• Establish evaluation approaches for LLM applications, covering retrieval quality, response accuracy, tool use, and failure handling.
• Guide deployment and operation on AWS or Azure, including monitoring, access controls, and production troubleshooting.
• Review critical designs and selected code changes, mentor engineers, and ensure appropriate testing and technical documentation.
• Run client technical discussions and progress reviews, explain decisions clearly, and escalate risks early.

Required experience and skills:

• At least 5 years of relevant engineering experience, with prior responsibility for leading a technical team.
• Demonstrated experience delivering a GenAI application to production, with a clear understanding of the challenges beyond a proof of concept.
• Strong understanding of LLM application architecture, including RAG, embeddings, retrieval, tool calling, and agent orchestration.
• Practical experience deploying and operating applications on AWS or Azure.
• A strong engineering foundation in Python, backend services, APIs, and data integration, sufficient to assess implementation quality and guide engineers.
• Experience evaluating and troubleshooting GenAI systems, including unreliable outputs, retrieval failures, latency, and cost.
• Ability to independently lead technical discovery, resolve ambiguity, and make defensible architecture decisions.
• Experience managing delivery for a small engineering team and handling client-facing requirements, scope, and progress discussions.
• Clear written and verbal communication, including the ability to explain technical constraints to nontechnical stakeholders.

Good to have:

• Experience with frameworks such as LangGraph, LangChain, or equivalent orchestration tools.
• Familiarity with CI/CD, containers, automated testing, and LLM observability.
• Experience with enterprise data security, sensitive information, and human review workflows.
• Experience in healthcare or other domains with complex workflows and data requirements.

What success looks like:

You can independently guide the team from requirements to a reliable production solution, keep clients informed, and identify delivery risks early. Your technical decisions are supported by evidence, your team has clear priorities, and projects progress with limited day-to-day oversight.