Join a global organization dedicated to improving health outcomes through technology. As a Lead AI/ML Engineer, you will be instrumental in developing and deploying advanced Large Language Model (LLM) agents and Retrieval-Augmented Generation (RAG) pipelines. These solutions will automate the detection, triage, and remediation of platform and application issues, significantly enhancing system efficiency.

This role sits at the critical intersection of machine learning engineering, system observability, and developer experience. You will architect robust systems for orchestration, implement essential guardrails, and establish evaluation frameworks to deliver impactful AI capabilities. Collaboration with SRE, InfoSec, and platform teams is key to building scalable, secure, and responsible AI solutions that integrate seamlessly into existing software development workflows. Embrace a culture of inclusion and continuous growth while advancing health optimization on a global scale.

Lead the design, development, and deployment of AI-powered solutions to tackle complex business challenges with a focus on responsible AI implementation.

Build and deploy production-grade LLM agents for automating the detection, triage, and remediation of platform and application issues. Design and optimize RAG pipelines utilizing diverse data sources such as runbooks, incident history, logs, code, and internal documentation, including expertise in chunking strategy, embedding selection, vector store design, and advanced search techniques. Implement sophisticated agent orchestration, managing tool/function calling, multi-step planning, agent handoffs, memory, and state management. Develop supporting infrastructure and software layers for agents, including tool wrappers, guardrails, human-in-the-loop approval mechanisms, and fallback behaviors. Take ownership of model and prompt engineering, encompassing model selection, optimization of prompts and context, output structuring, cost/latency tuning, and applying fine-tuning or parameter-efficient techniques as needed. Construct evaluation pipelines and define quality metrics for agent and RAG performance, such as retrieval precision/recall, groundedness, hallucination rates, and Mean Time To Resolution (MTTR) impact, iterating based on analytical results. Integrate agents with observability and security platforms, leveraging APIs and Model Context Protocol (MCP) tool interfaces to deliver capabilities directly within developer workflows. Evaluate emerging AI trends and contribute reusable patterns, components, and documentation to the enterprise AI development lifecycle. Utilize enterprise-approved AI tools to streamline workflows, automate tasks, and drive continuous improvement, adhering to all company policies and directives.

A Bachelor's degree or equivalent practical experience, such as 10+ years in software engineering or machine learning engineering, is required.

Possess a minimum of 10 years of experience in software engineering or machine learning engineering. Demonstrate 10+ years of proficiency in programming languages such as Java, C#, Python, or Go. Have over 6 years of experience integrating third-party APIs and developing backend services that operate in production environments. Bring 6+ years of experience working with cloud platforms (Azure, AWS, or GCP), containers, and CI/CD pipelines. Showcase 2+ years of hands-on experience building with LLMs, including expertise in prompt engineering, tool/function calling, and agent or multi-step orchestration. Accumulate 2+ years of experience designing and deploying RAG systems in production, covering embeddings, vector databases (e.g., Azure AI Search, Pinecone, Milvus, pgvector, FAISS), and retrieval evaluation. Possess 2+ years of experience with Python, including practical knowledge of agent frameworks like LangGraph, LangChain, LlamaIndex, Semantic Kernel, or CrewAI. Have 2+ years of experience building LLM evaluation and testing workflows, moving beyond manual spot checks.