Lead AI Engineer

This is a fully remote position, open to applicants in United States.

📋 Description

• Take charge of designing and delivering the agentic AI functionalities for the NBA platform.

• Develop, construct, and oversee AI agent workflows for intelligent analysis, recommendations, and automation.

• Collaborate with the engineering team to write and deploy production code.

• Design multi-step agentic pipelines that integrate the platform's data layer, decision-making outputs, and activation channels.

• Incorporate large language models such as Claude and GPT into the platform workflows.

• Utilize prompt engineering, tool usage, structured output management, and context control.

• Work closely with frontend and product teams to provide AI-driven analysis and recommendations in the Command and Control UI and other interfaces for operators.

• Create evaluation frameworks to assess the quality of AI outputs.

• Ensure the reliability, auditability, and safety of agentic workflows within a regulated healthcare environment.

• Lead a small team of engineers and contractors.

• Set expectations, assess contractor work, and uphold quality standards.

• Demonstrate best practices in AI-assisted development throughout the engineering organization.

• Be open to occasional travel to Humana offices for training or meetings.

⛳️ Requirements

• Over 6 years of experience in software or ML engineering.

• A minimum of 1–2 years focusing on LLM integration, agentic AI, or AI product engineering.

• Hands-on experience in developing production agentic systems, including multi-step pipelines, tool orchestration, structured output handling, and multi-turn conversation management.

• Production experience with RAG patterns and vector search.

• Proficient in Python engineering.

• Experience in integrating LLM APIs, such as Anthropic, OpenAI, or similar, into real-world applications.

• Demonstrated ability to lead a small team or pod through successful delivery and manage contractor resources effectively.

• Strong judgment in the appropriate application of AI in regulated, member-facing scenarios.

• Ability to articulate agentic architecture concepts to both engineers and product owners.

• Extensive familiarity with AI productivity tools like Claude and Copilot.

• Preferred: Experience in orchestrating multi-agent systems.

• Preferred: Background in integrating agentic AI into custom enterprise software and external systems such as Salesforce, Adobe Experience Platform, or claims platforms.

• Preferred: Experience in creating AI-enhanced analytics or insights within business intelligence or operational user interfaces.

• Preferred: Background in healthcare, insurance, or other regulated sectors.

• Preferred: Experience with AI evaluation frameworks and techniques for detecting output quality drift.

• Preferred: Familiarity with the Anthropic Claude API and Claude Agent SDK.

• Typical working hours are Monday to Friday, 8 hours per day, 5 days per week.

• Minimum home internet speed of 25 Mbps download and 10 Mbps upload.

• A dedicated workspace that allows for uninterrupted work to protect member PHI/HIPAA information.

🏝️ Benefits

• Bonus incentive plan based on company and/or individual performance.

• Medical benefits.

• Dental benefits.

• Vision benefits.

• 401(k) retirement savings plan.

• Paid time off.

• Company holidays.

• Personal holidays.

• Paid parental leave.

• Paid caregiver leave.

• Short-term disability.

• Long-term disability.

• Life insurance.

• Opportunities for occasional travel for training, meetings, and/or conferences.

• Remote work arrangement.

• Home or hybrid home/office work setup.

• Dedicated workspace and internet requirements to facilitate remote work.