Senior AI Engineer

Humana is hiring a Senior AI Applied Engineer to build and operate production AI systems at scale for processing clinical documents using large language models. This role drives end-to-end ownership across application delivery, LLM orchestration, evaluation, infrastructure, and production operations, with an emphasis on accuracy, reliability, auditability, and scalability in a regulated healthcare setting.

Core Responsibilities

• Design, develop, and deploy full-stack AI applications, including frontend experiences, APIs, backend services, and data pipelines.
• Build and optimize LLM-based workflows for information extraction, classification, retrieval, summarization, and agentic processes.
• Create reliable LLM prompting strategies, structured output frameworks, tool-calling capabilities, and fallback mechanisms.
• Design and implement retrieval-augmented generation (RAG) systems using embeddings, vector databases, and semantic search technologies.
• Develop evaluation frameworks, including benchmark datasets, regression testing, quality metrics, and human review workflows.
• Implement human-in-the-loop processes so clinicians and domain experts can validate AI outputs and provide feedback for continuous improvement.
• Build and maintain document-processing pipelines, including OCR, document ingestion, metadata extraction, indexing, and search.
• Optimize AI systems for accuracy, latency, reliability, scalability, and cost efficiency.
• Implement observability practices for production systems, including monitoring, logging, alerting, and incident response.
• Deploy and operate services in cloud-native environments using Kubernetes, Docker, CI/CD pipelines, and supporting infrastructure tooling.
• Collaborate with product, engineering, clinical, and operational stakeholders to translate complex requirements into scalable solutions.
• Ensure solutions meet privacy, security, compliance, and auditability requirements in a regulated healthcare environment.

Required Qualifications

• Bachelor’s degree in Computer Science, Engineering, Mathematics, Statistics, or another quantitative or related technical discipline, or an equivalent combination of education and practical experience.
• 5+ years of experience building and operating production software systems.
• Experience developing backend services, APIs, distributed systems, or data-intensive applications.
• Hands-on experience integrating LLMs into production applications beyond basic chat interfaces, including structured outputs, tool calling, RAG, agents, or multi-step workflows.
• Experience with at least one major AI platform or model provider such as OpenAI, Anthropic, Google, Azure AI, or AWS Bedrock.
• Strong programming skills in Python and/or TypeScript/JavaScript.
• Experience debugging, monitoring, and supporting production applications used by real customers.
• Ability to work independently, navigate ambiguity, and take ownership from concept through deployment.

Preferred Qualifications

• Experience building AI systems where LLMs are part of the critical production workflow.
• Experience designing evaluation frameworks, testing strategies, prompt versioning, tracing, and model performance monitoring.
• Experience with agentic architecture, Model Context Protocol (MCP), tool orchestration frameworks, or autonomous workflows.
• Experience with React, Next.js, modern frontend development, and full-stack application architecture.
• Experience deploying and operating workloads in Kubernetes, Docker, and cloud environments.
• Experience with modern CI/CD practices and infrastructure automation.
• Experience working in regulated industries such as healthcare, financial services, or government.
• Familiarity with privacy, compliance, governance, and data protection requirements.
• Experience using AI-assisted development tools to improve engineering productivity and software quality.
• Strong problem-solving, communication, and collaboration skills.

Technology Stack

• TypeScript
• React / Next.js
• Python
• PostgreSQL
• Gemini on Vertex AI
• OCR and Document AI technologies
• Docker
• Kubernetes
• Modern CI/CD platforms and tooling
• OpenAI, Anthropic, Google, Azure AI, AWS Bedrock

Location, Work Style, and Schedule

Location: Louisville, KY (hybrid). Hybrid schedule requires employees to work three days per week in the office and the remaining days remotely.

Weekly hours: 40.

Qualified candidates must currently reside within, or be willing to relocate to, a commutable distance from one of the talent markets.

Compensation and Incentives

• Pay range: USD 141,100 - 194,000 per year.
• This job is eligible for a bonus incentive plan.

Benefits

• Medical, dental and vision benefits
• 401(k) retirement savings plan
• Time off (including paid time off, company and personal holidays, paid parental and caregiver leave)
• Short-term and long-term disability
• Life insurance