Senior AI Engineer

Senior AI Engineer Remote role open to all U.S. states. ESSENTIAL FUNCTIONS AND RESPONSIBILITIES • Owns a build stream end to end within a pod: problem shaping with the Principal, implementation, production operation, and instrumentation of the outcome the business said it would measure. • Designs, builds, and operates production Generative AI agents, workflows, and applications - including request orchestration, tool execution, state management, and interaction with enterprise systems. • Develops full-stack software in Python and React, shipping both the service and the interface a business user touches. • Owns deployment and operation on AWS, with infrastructure as code in Terraform and CI/CD in GitHub Actions, including environments, secrets, and repeatable promotion to production. • Implements evaluation, observability, and human-in-the-loop controls for AI systems: provenance on material outputs, confirmation on consequential claims actions, and evidence that a workflow is ready to move up the autonomy ladder. • Implements authentication, authorization, logging, monitoring, and error handling to meet enterprise security, auditability, PHI, and reliability requirements. • Integrates AI services with enterprise and legacy systems - including APIs, data platforms, and event streams - using approved, non-invasive patterns and versioned contracts. • Stewards a shared capability as assigned (context, documents, agents, or assurance), with authority to block a duplicate build in another pod. • Embeds with vendor delivery teams for co-development when the stream requires it: shared repositories in Sedgwick accounts, shared definition of done, not acceptance testing after a demo. • Sits with examiners, nurse reviewers, or operations staff; watches the work; and turns that into scoped services, workflows, and UI changes. • Provides technical guidance and mentoring to Junior AI Engineers, promoting engineering standards, code quality, and operational excellence. • Troubleshoots and leads root cause analysis and performance optimization for latency, throughput, cost, correctness, and reliability of production AI services. • Evaluates and recommends improvements to architecture, platform capabilities, and engineering process for the stream and the shared substrate. ADDITIONAL FUNCTIONS AND RESPONSIBILITIES • Performs other duties as assigned. • Travel as required, including on-site work with claims or Managed Care operations and with vendor delivery teams. QUALIFICATIONS Education & Licensing Bachelor's degree in Computer Science, Engineering, or a related quantitative discipline from an accredited college or university required. Master's degree preferred. Experience Six (6) + years of software engineering experience, with at least three (3) years shipping production Generative AI agents, workflows, or applications - including evaluation, failure handling, and a human review loop - or an equivalent combination of education and experience. Hands-on experience building and operating production workloads on AWS required. Cloud certification without production ownership is not sufficient. Hands-on experience with Python, React, GitHub Actions, and Terraform required, including ownership of CI/CD and infrastructure rather than editing templates. Experience embedding with business users or a vendor delivery team to co-develop, rather than receiving a completed specification, preferred. Experience in insurance, claims, healthcare, or another heavily regulated operational domain preferred. Skills & Knowledge • Strong full-stack engineering skills in Python and React, with solid working knowledge of SQL, REST APIs, and service design • Hands-on AWS: has built, deployed, and operated production services, including networking, identity, and operational concerns sufficient for a regulated environment • Hands-on GitHub Actions and Terraform: owns pipelines and infrastructure as code, including review, drift, and recovery • Production command of Generative AI agents, workflows, and applications - tool use, orchestration, evaluation, and human-in-the-loop patterns - sufficient to ship and run, not only prototype • Ability to implement services in alignment with enterprise architecture, governance, PHI handling, and compliance requirements • Ability to sit with examiners or operations staff and leave with scoped work; comfortable as the only engineer in that room • Ability to work collaboratively in a fast-paced Transformation Office, including pairing with vendor engineers when required • Strong mentoring, collaboration, and technical communication skills • Experience with machine learning, model fine-tuning, and/or graph databases (e.g. Neo4j) preferred • Experience with PydanticAI (or equivalent agent framework), agent observability, and AI Ops / LLMOps a plus • Ability to meet or exceed Performance Competencies WORK ENVIRONMENT When applicable and appropriate, consideration will be given to reasonable accommodation. Mental: Clear and conceptual thinking ability; excellent judgment, troubleshooting, problem solving, analysis, and discretion; ability to handle work-related stress; ability to handle multiple priorities simultaneously; and ability to meet deadlines Physical: Computer keyboarding, travel as required Auditory/Visual: Hearing, vision and talking