AI Engineer — End-to-End Healthcare Claims Agent

Aimlroles; Northern (KY); Hybrid; USD 130,000 - 200,000; Full time

Benefits offered by this job

Work from anywhere in the US

Top Medical/Dental/Vision offerings

FSA/HSA

Tuition reimbursement

Competitive salary with 401(k) match

Unlimited PTO

Flexible work environment

Job summary

Machinify is hiring an L4 AI Engineer to design agent systems from scratch, auditing medical claims end-to-end, and delivering defensible findings for regulatory review. You will decide on architecture, tool usage, and context strategy, shaping systems that operate with high accuracy and reliability in a complex domain.

Join a production-grade environment that emphasizes measurable results, deep domain knowledge in healthcare, and collaboration with a team that values engineering rigor and tool

Qualifications

• 2-4 years of applied ML / AI engineering experience with a relevant degree or a Master's with no prior industry experience.
• Strong Python engineering with clean abstractions and tested code.
• Hands-on understanding of agent loops and tool integration.
• Experience with major agent SDKs and pragmatic tradeoffs.
• Ability to design context loading, prompts, and long-running tasks with grounding.

Responsibilities

• Design agent systems from first principles and defend architecture choices.
• Engineer the context, prompts, and tool surfaces for reliable outputs.
• Drive evaluation rigor with pre-built evals and metric tracking.
• Utilize Claude Code, Codex, and related tools to plan, scaffold, and debug work.
• Become a domain expert in healthcare claims, coding guidelines, and clinical records.

Skills

Agent loops understanding

Python engineering

OpenAI / Claude Codex

VS Code & Git

Evaluation metrics

Education

Bachelor's degree in CS/Math/Engineering or equivalent

Tools

OpenAI Agents SDK

Claude Code / Codex

LangGraph

Job description

Machinify is hiring an L4 AI Engineer to design agent systems from scratch, auditing medical claims end-to-end, and delivering defensible findings for regulatory review. You will decide on architecture, tool usage, and context strategy, shaping systems that operate with high accuracy and reliability in a complex domain.

Join a production-grade environment that emphasizes measurable results, deep domain knowledge in healthcare, and collaboration with a team that values engineering rigor and tool