1 day ago
Remote, United StatesSenior
Responsibilities
- Own a build stream from problem shaping through implementation, production operation, instrumentation, and business-outcome measurement.
- Design, build, deploy, and operate production Generative AI agents, workflows, and applications.
- Develop full-stack software in Python and React, including services and business-user interfaces.
- Own AWS deployments, Terraform infrastructure as code, environments, secrets, and GitHub Actions CI/CD promotion pipelines.
- Implement AI evaluation, observability, provenance, confirmation controls, and human-in-the-loop workflows.
- Implement authentication, authorization, logging, monitoring, error handling, auditability, PHI protections, and reliability controls.
- Integrate AI services with enterprise and legacy systems, APIs, data platforms, and event streams using versioned contracts.
- Embed with business users and vendor delivery teams to co-develop services, workflows, and UI changes.
- Mentor Junior AI Engineers and promote engineering standards, code quality, and operational excellence.
- Lead root cause analysis and optimize production AI services for latency, throughput, cost, correctness, and reliability.
- Evaluate and recommend improvements to architecture, platform capabilities, and engineering processes.
- Travel as required for on-site work with claims, Managed Care operations, and vendor delivery teams.
Requirements
- Bachelor’s degree in Computer Science, Engineering, or a related quantitative discipline, or an equivalent combination of education and experience, is required; a master’s degree is preferred.
- At least six years of software engineering experience, including at least three years shipping production Generative AI agents, workflows, or applications with evaluation, failure handling, and human review loops.
- Hands-on experience building and operating production workloads on AWS is required; cloud certification without production ownership is insufficient.
- Hands-on experience with Python, React, GitHub Actions, and Terraform, including ownership of CI/CD and infrastructure rather than template editing.
- Strong full-stack engineering skills and working knowledge of SQL, REST APIs, and service design.
- Production experience with Generative AI agents, workflows, tool use, orchestration, evaluation, and human-in-the-loop patterns.
- Ability to implement services meeting enterprise architecture, governance, PHI handling, compliance, security, and operational requirements.
- Experience embedding with business users or vendor delivery teams to co-develop solutions is preferred.
- Experience in insurance, claims, healthcare, or another heavily regulated operational domain is preferred.
- Experience with machine learning, model fine-tuning, or graph databases such as Neo4j is preferred.
- Experience with PydanticAI or an equivalent agent framework, agent observability, and AI Ops or LLMOps is a plus.
- Strong mentoring, collaboration, technical communication, troubleshooting, problem-solving, judgment, and prioritization skills.
Benefits
- Remote role open to U.S.-based candidates.
- Travel and on-site work may be required with claims or Managed Care operations and vendor delivery teams.
- Sedgwick offers a caring culture and work-life balance.
- Reasonable accommodation will be considered when applicable and appropriate.
- Sedgwick is an Equal Opportunity Employer and a Drug-Free Workplace.
About Sedgwick
Sedgwick provides third‑party claims administration, risk and benefits services for employers, insurers, and public entities, spanning workers’ compensation, property and liability, disability and absence, and product recall. It sells outsourced claims management and related technology on a fee‑for‑service basis, supported by analytics and AI‑enabled tools, across operations in more than 80 countries. Founded in 1969 and headquartered in Memphis, Tennessee, Sedgwick is privately held under The Carlyle Group.