Staff AI Engineer — Boston, MA

Staff AI Engineer (Agentic AI / LLM Systems) required by a leading healthcare technology company transforming how healthcare organisations leverage data, analytics and AI to improve patient outcomes. The business has an established platform supporting complex healthcare workflows and is investing heavily in building next-generation AI capabilities.

You'll take ownership of how AI agents behave, make decisions and operate reliably in real-world production environments. Working closely with Product and Engineering, you'll design and optimise agentic systems, develop robust evaluation frameworks, and ensure AI models remain accurate, grounded and safe at scale.

What we offer

• Base Salary: $250,000–$270,000 + 25–30% Bonus

• Remote-Friendly US

• Staff Level, with potential for Principal

Requirements

• Ideally 7–10 years of experience across software engineering, AI/ML and production systems.

• Strong hands-on experience building and deploying LLM or agentic AI systems in production.

• Experience with RAG architectures, retrieval systems, context engineering and memory management.

• Strong understanding of model evaluation, failure analysis, prompt engineering and AI guardrails.

• Experience developing human-in-the-loop workflows, fallback mechanisms and escalation strategies.

• Background in a highly regulated industry, ideally healthcare or financial services.

• Strong software engineering capabilities combined with practical data science and machine learning experience.

• Familiarity with AWS AI/ML services, particularly Bedrock and SageMaker.

Bonus

• Experience applying AI to healthcare data, clinical workflows or population health.

• Experience designing long-horizon, multi-turn and multi-agent AI systems.

• Experience developing model cards, evaluation rubrics and production AI governance frameworks.

Responsibilities

• Design, develop and optimise agentic AI systems operating across complex, real-world workflows.

• Architect RAG, retrieval, context and memory systems to ensure models remain grounded in accurate source data.

• Develop and refine prompts, tool-use strategies and context templates to improve agent performance.

• Build production evaluation frameworks to measure accuracy, reliability, regressions and failure modes.

• Implement AI guardrails, confidence thresholds and human-in-the-loop escalation mechanisms.

• Diagnose model failures and determine whether improvements are required across prompts, retrieval, context or memory.

• Optimise AI systems for performance, latency, reliability and cost efficiency.

• Own model readiness assessments, comparative evaluations and production release decisions.

• Partner with Product and Engineering teams to translate production feedback into scalable AI improvements.

Benefits

• Competitive Base Salary and Performance Bonus

• Potential Equity Participation

• Flexible, Remote-Friendly Working Environment

• Professional Development Opportunities

• Collaborative, Mission-Driven Engineering Culture

• Opportunity to Influence AI Product Strategy and Architecture

Why Join?

This is an opportunity to take a leading role in shaping how agentic AI is deployed across a well-established healthcare technology platform. Rather than simply developing models, you'll own the reliability, safety and performance of AI systems operating in complex, highly regulated environments.

You'll have significant technical ownership, work closely with senior Product and Engineering stakeholders, and help define the standards for production-ready AI within an organisation focused on improving healthcare delivery and patient outcomes.

Interested in learning more? Apply today.