Lead AI Systems Engineer: LLMs, RAG & Responsible AI

Humana Inc; Atlanta (GA); On-site; USD 129,000 - 178,000; Full time

Job summary

Humana Inc. is seeking a Lead Software Engineer to architect and drive AI systems within CenterWell's care delivery stack. You will own end-to-end architecture for LLM-powered features, coordinate with product, clinical teams, and data stakeholders, and guide production deployments.

The role emphasizes HIPAA compliance, Responsible AI practices, and building scalable multi-agent workflows. Strong Python/TypeScript skills and experience with LangChain/LlamaIndex are essential.

Qualifications

• B.S. or M.S. in Computer Science, Engineering, or related field (or equivalent experience).
• 8+ years of software engineering experience, with 4+ years focused on production AI/ML systems.
• Deep, hands-on experience building with large language models and orchestration frameworks (LangChain, LlamaIndex, or equivalent).
• Strong proficiency in Python, Typescript and modern ML tooling (Hugging Face, PyTorch, or similar).
• Proven experience designing and deploying RAG pipelines and vector search systems in production.
• Working knowledge of model fine-tuning approaches (LoRA, RLHF, instruction tuning, or equivalent).
• Experience designing and implementing custom LLM and agent evaluation frameworks, including automated eval pipelines, benchmark construction, and output quality assessment at scale
• Experience designing and building multi-agent AI systems, including agent orchestration, tool use, and sandboxed execution environments
• Demonstrated ownership of complex AI systems end-to-end, from architecture through production operation
• Understanding of HIPAA requirements and secure handling of protected health information (PHI)
• Strong written and verbal communication skills across technical and non-technical audiences
• Hands-on experience with AI-assisted development tools and LLM coding harnesses (Claude Code, Pi Agent, Cursor, Codex, or similar)

Responsibilities

• Technical Architecture and Ownership:** Design and own the end-to-end architecture of Centerwell's AI systems, including LLM-powered clinical tools, RAG pipelines, harnesses, agent-based workflows, and intelligent automation. Make and communicate foundational technical decisions in close collaboration with the broader engineering team.
• Model Development and Fine-Tuning:** Evaluate, select, and where appropriate guide the fine-tuning of foundation models. Establish model evaluation frameworks that prioritize safety, accuracy, and clinical relevance.
• Clinical and Product Partnership:** Collaborate closely with product managers, designers, clinicians, and data stakeholders to understand care delivery workflows and translate them into well-scoped, high-impact AI features.
• HIPAA Compliance and Responsible AI:** Ensure all AI systems are designed, deployed, and monitored in compliance with HIPAA and Humana's Responsible AI standards, including participation in AIRB and Responsible AI Council review processes where applicable.

Skills

Python

TypeScript

LangChain

LlamaIndex

Hugging Face

PyTorch

RAG pipelines

Vector search

LoRA

RLHF

Evaluation frameworks

Multi-agent systems

Agent orchestration

PHI handling

HIPAA knowledge

LLM harnesses

Claude Code

Pi Agent

Cursor

Codex

Education

B.S. or M.S. in Computer Science, Engineering, or related field

Tools

Claude Code

Pi Agent

Cursor

Codex

Job description

Humana Inc. is seeking a Lead Software Engineer to architect and drive AI systems within CenterWell's care delivery stack. You will own end-to-end architecture for LLM-powered features, coordinate with product, clinical teams, and data stakeholders, and guide production deployments.

The role emphasizes HIPAA compliance, Responsible AI practices, and building scalable multi-agent workflows. Strong Python/TypeScript skills and experience with LangChain/LlamaIndex are essential.