Lead AI Engineer Remote

Salary: $145,500 - 249,500 per year Requirements:

• We require a bachelors or masters degree in Computer Science, Artificial Intelligence, Data Science, or a related discipline.
• We need 8+ years of overall software or AI engineering experience.
• We require 2+ years of direct, hands-on experience building and deploying GenAI or LLM applications in production.
• We need strong Python development skills, as this is our primary language for AI engineering.
• We require demonstrated experience with RAG pipelines, vector databases, and agentic architectures.
• We require a drivers license and access to reliable transportation.
• Preferred qualifications include AWS AI or GenAI certifications, AWS Cloud Practitioner or Developer Associate, and AI/ML Specialty credentials.
• Preferred experience includes Graph RAG, Semantic Kernel, human-in-the-loop systems, fine-tuning open-source LLMs with LoRA or QLoRA, and Amazon Connect integrations with Bedrock Agents via Lex V2.

• We design and build production-grade RAG pipelines using LangChain and LangGraph for stateful agentic workflows.
• We develop and support knowledge base chatbots with semantic search, source attribution, and multi-turn memory.
• We implement advanced retrieval methods such as hybrid search, HyDE, and hierarchical or small-to-big chunking.
• We build and coordinate multi-agent orchestration solutions using Agentic RAG patterns such as Corrective RAG and Self-RAG.
• We integrate LLMs including Claude, GPT-4o, Llama 3, and Mistral through APIs and open-source hosting platforms.
• We design and manage vector databases such as Pinecone, Weaviate, or PGVector for semantic knowledge storage.
• We build AWS Bedrock-based solutions using Bedrock Agents, Knowledge Bases, and Guardrails.
• We establish evaluation frameworks with Ragas and maintain Golden Datasets for CI and AI testing.
• We implement LLM observability with LangSmith or Phoenix to trace calls, diagnose hallucinations, and monitor costs.
• We apply PII redaction to ingested documents and enforce data security using Model Context Protocol.
• We deploy AI backends with FastAPI and Docker, supported by OpenTelemetry for system-wide monitoring.
• We collaborate with Solution Architects to produce HLDs, LLDs, and developer documentation for AI components.

• AI
• AWS
• Cloud
• Docker
• FastAPI
• Fine-tuning
• Support
• LLM
• OpenTelemetry
• Phoenix
• Python
• RAG
• Security
• Agentic AI
• API
• MCP
• UX UI Design

More:

We are Optum, a global organization using technology to help millions of people live healthier lives and improve health outcomes. Our culture emphasizes inclusion, strong peer support, comprehensive benefits, and career development opportunities. This role is remote within the U.S., with a requirement for employees in the Minneapolis or Washington, D.C. area to work onsite at least four days per week. We offer a comprehensive benefits package, incentive and recognition programs, equity stock purchase, and 401(k) contribution, with a salary range of $145,500 to $249,500 annually for full-time employment. We are committed to health equity, environmental responsibility, and providing an inclusive workplace for all.

last updated 33 week of 2026