AI Engineer
Build full-stack AI prototypes and agentic systems to pressure-test venture ideas. Requires 3+ years building production AI applications with strong frontend/backend fluency and frontier coding agent expertise.
AI Engineer
Leads development of agentic AI platform to autonomously resolve healthcare insurance claim denials using multi-agent workflows, RAG systems, and LLMs. Requires 5+ years in production ML engineering with Python and frameworks like PyTorch.
150k – 275kNew York, NYML EngineeringHybrid5+ YOE
About the role
What you'll do
- Design and build the architecture for our agentic AI system that autonomously resolves insurance claim denials
- Develop specialized AI agents for denial classification, root cause analysis, evidence retrieval, policy reasoning, and appeal generation
- Implement multi-agent orchestration frameworks that coordinate complex workflows across research, decision-making, and document generation
- Build and optimize RAG systems to retrieve relevant clinical documentation, billing records, and payer policy information
- Create evaluation frameworks and feedback loops to continuously improve agent performance and reliability
- Design prompt engineering strategies and fine-tuning approaches to optimize LLM behavior for healthcare billing workflows
- Work closely with billing managers to understand denial resolution workflows and translate them into agent behaviors
- Collaborate with the engineering team on production infrastructure for deploying and monitoring AI agents at scale
- Actively contribute to building the team's AI/ML vision and technical roadmap
- Collaborate on code reviews and technical design documents to ensure code quality and distribute knowledge
We'd love to hear from you if…
- 5+ years of experience in machine learning engineering, with a focus on building production AI systems and deploying models at scale
- Strong experience with machine learning frameworks (PyTorch, TensorFlow, or JAX)
- Experience working with healthcare data or understanding of medical billing workflows is a plus
- Proficiency in:
- Python and modern ML frameworks (PyTorch, TensorFlow, or JAX)
- LLM technologies including prompt engineering, fine-tuning, and RAG systems
- Vector databases and semantic search systems
- Building reliable, production-grade AI systems with proper evaluation and monitoring
- MLOps practices including model versioning, A/B testing, and performance tracking
- Working with APIs and integrating AI systems into broader product workflows
Skills
PythonPyTorchTensorFlowJAXLLMPrompt EngineeringRAGMLOpsVector DatabasesAPIs
Similar roles
ML Engineering jobsMachine Learning Engineer
Build and deploy ML models for entity resolution and knowledge graph expansion on large-scale China-related data. Requires 4+ years clustering ML experience and end-to-end production ML with Python/SQL.
Research Engineer, Post-Training
Research Engineers design and run post-training workflows, build evaluation infrastructure, and turn frontier AI techniques into reliable production systems for enterprise customers. Requires experience with fine-tuning, RLHF, reward modeling, and strong experimentation skills.
Research Engineer, Agents
Research Engineers build and productionize agentic AI systems, designing compound architectures, evaluation frameworks, and reliable execution for enterprise workflows. Requires strong Python skills, systems reasoning, and experience building agents with tools, retrieval, planning, and memory.