Lead AI Engineer

Join us as we work to create a thriving ecosystem that delivers accessible, high-quality, and sustainable healthcare for all.

Position Summary: We are looking for a Lead AI Engineer in Bangalore to help build Messaging 3.0, our next-generation intelligent patient communication platform. You will design and build production-grade AI agents end to end - from LLM orchestration, tool integration, and evaluation to guardrails, observability, reliability, and production operations. You will also be the technical lead for this initiative, setting the technical direction and mentoring engineers through influence rather than formal authority.
In your first 90 days, you will help establish the foundation for the AI-driven Intelligent Messaging platform, including core services, supporting services, Temporal workflows, and two initial agents: the Notification AI Agent and Cadence Outreach AI Agent.
Over your first year, you will take these agents to production and build next-best-action intelligence so they can act autonomously and reliably toward the intended outcome of each message. You will also ensure the new architecture continues to support the important use cases handled by our existing legacy monolith and microservices.

About the Team: The Messaging team is building Messaging 3.0 - moving from static notifications and campaign-based outreach to intelligent, agent-orchestrated patient communication.
Our AI agents will use patient context, preferences, workflow state, and tools to:

• Determine the next best action.
• Personalize patient communication.
• Select the right communication channel.
• Manage the interaction through to completion.

This is a mix of greenfield and brownfield development. You will build new services while also replacing or wrapping existing systems that support live patient messaging in production today.

Essential Job Responsibilities

• Lead the technical design and development of the Messaging 3.0 AI platform.
• Build production-grade AI agents using LLM orchestration, tools, context, evaluation, guardrails, and observability.
• Design and build scalable services using Java, Spring Boot, microservices, Kubernetes, and AWS.
• Design and implement Temporal workflows for long-running and failure-prone processes, including retries and compensation.
• Build and take the Notification AI Agent and Cadence Outreach AI Agent to production.
• Build next-best-action intelligence that enables agents to act autonomously and predictably toward the intended message outcome.
• Identify and solve AI agent reliability and unpredictability issues in production.
• Ensure the new architecture continues to cover use cases supported by the existing legacy monolith and microservices.
• Drive high-quality delivery and continuously improve engineering speed, quality, and reliability.
• Provide technical leadership and mentorship to engineers through influence rather than formal authority.

Additional Job Responsibilities

• Work across both greenfield and brownfield systems.
• Collaborate with engineers and stakeholders to establish technical direction and alignment.
• Own technical outcomes end to end, from design through production.
• Adapt as requirements and the architecture evolve.
• Evaluate and adopt new AI and agent technologies as the space changes.
• Build systems that are reliable and predictable in production, not just successful in demos.
• Understand existing messaging systems well enough to avoid gaps in functionality during modernization.

Expected Education & Experience

• 8+ years of software engineering experience, including 2+ years building AI agents.
• Strong hands-on experience with Java and Spring Boot in production.
• Strong system design and software architecture experience, including architectural trade-offs and decision-making.
• Production experience deploying and operating services on Kubernetes.

Looking to get Placed? Try our Placement Guarantee Plan

Get Hired
• Experience with Temporal or an equivalent durable workflow orchestration framework.
• Hands-on experience with LangGraph, LangChain, or an equivalent agent framework.
• Experience taking an AI/agentic system from prototype to reliable production.
• Strong understanding of AI/agent engineering, including reliability, evaluation, guardrails, and observability.
• Production experience with AWS and practical experience making AWS architecture decisions.
• Experience with Kafka, Postgres, Redis, Helm, Datadog, or equivalent observability tools is a plus.
• Data science experience is a plus.
• GenAI experience beyond agent frameworks, such as prompt/model evaluation or fine-tuning, is a plus.
• Strong communication, collaboration, and technical leadership skills.
• Comfortable working in ambiguous and evolving environments and leading through influence.