Senior AI or ML Engineer - Hybrid in Austin, TX, Chicago, IL, or Minneapolis, MN

UnitedHealth Group•Minneapolis, MN

6d•Hybrid

About The Position

Optum is a global organization that delivers care, aided by technology to help millions of people live healthier lives. The work you do with our team will directly improve health outcomes by connecting people with the care, pharmacy benefits, data and resources they need to feel their best. Here, you will find a culture guided by inclusion, talented peers, comprehensive benefits and career development opportunities. Come make an impact on the communities we serve as you help us advance health optimization on a global scale. Join us to start Caring. Connecting. Growing together. We’re excited to share an opportunity to join a cutting-edge project involving the development and enhancement of a voice-based bot platform built on top of an LLM (Large Language Model) framework. The scope of work includes collaborating on a highly scalable, consumer-facing system designed for production environments with significant traffic. Ideal candidates should be enthusiastic about emerging technologies in the LLM space, as this role offers hands-on experience with advanced tools and the chance to explore innovative solutions within a rapidly evolving AI landscape. If you are located in Austin, Chicago or Minneapolis, you will have the flexibility to work remotely, as well as work in the office as you take on some tough challenges. For all hires in the Minneapolis or Washington, D.C. area, you will be required to work in the office a minimum of four days per week.

Requirements

5+ years of experience in delivering AI/ML projects in a production environment, preferably consumer-facing and high-traffic systems
5+ years of client-side application development, with a solid track record of building scalable and performant user-facing applications
5+ years of hands-on coding experience in JavaScript or Python—must be comfortable writing production-quality code
3+ years of hands-on development experience with Large Language Models (LLMs), including prompt engineering, fine-tuning, or custom LLM orchestration
2+ years of experience working with agentic AI architectures, including task decomposition, memory management, and autonomous agent workflows

Nice To Haves

Experience working with AWS Bedrock, including deploying and orchestrating foundation models within a managed environment
Hands-on experience integrating conversational AI platforms like Amazon Lex V2 with backend services or bots, especially for voice-based or multi-turn conversations
Familiarity with AWS Lambda for building scalable, serverless microservices that integrate with LLM workflows or bot architectures
Experience with Amazon Kendra, Amazon SageMaker, or AWS Step Functions is a plus, especially in the context of LLM-powered knowledge retrieval or orchestration
Understanding of event-driven architecture and serverless patterns using AWS SNS/SQS, API Gateway, and DynamoDB
Experience deploying and monitoring LLM-enabled bots in Amazon Connect or other customer engagement platforms
Experience in deploying scalable solutions to complex problems, from defining the problem, implementing the solution, and launching the new product successfully
Familiarity with CI/CD pipelines on AWS (e.g., CodePipeline, CodeBuild) for automating model updates and bot deployments
Proven skills in the following: NLP, NLU, NLI
Models: GPT, Llama, Mistral
Model Optimization
Retrieval & Ranking, RAG, RAGAS

Responsibilities

Help design and develop the next generation of NLP, ML & AI products, and services for healthcare
Develop machine learning and deep learning models and systems in domains including, but not limited to: NLP, NLU, NLG, SLU and multidimensional time series forecasting among others
Exposure in RAG, LangChain, VectorDBs
Ability to Quantize, Optimize GenAI models
Manage NLP & ML models lifecycle for a suite of products
Run large complex proof-of-concepts for the healthcare business
Manage prioritization and technology work for building NLP, ML & AI solutions
Lead the full end-to-end machine learning development process including data ingestion and preparation, feature engineering, analysis and modeling, model deployment, performance tracking and documentation
Establish best practices for end-to-end deep learning and machine learning development cycle to ensure rigor in process and quality in outcome
Work with a great deal of autonomy to find solutions to complex problems
Comply with the terms and conditions of the employment contract, company policies and procedures, and any and all directives (such as, but not limited to, transfer and/or re-assignment to different work locations, change in teams and/or work shifts, policies in regards to flexibility of work benefits and/or work environment, alternative work arrangements, and other decisions that may arise due to the changing business environment). The Company may adopt, vary or rescind these policies and directives in its absolute discretion and without any limitation (implied or otherwise) on its ability to do so