Senior Forward Deployed Engineer

Senior Forward Deployed Engineer

Hippocratic AI is building the world's first healthcare-only, safety-focused LLM platform. As a Senior Forward Deployed Engineer, you're an AI systems designer who drives innovation and solves cutting-edge problems in healthcare conversational AI. You develop sophisticated AI systems, anticipate customer needs, and shape how Hippocratic AI deploys advanced LLM techniques  balance ambitious innovation with production reliability, combining deep AI expertise with architectural thinking.

This role owns the full technical vision for complex AI deployments: architecting advanced RAG systems, designing sophisticated tool-calling and MCP integration patterns, implementing cutting-edge LLM techniques, anticipating and solving customer problems proactively, ensuring production reliability across multiple systems, and mentoring other engineers. You work closely with Deployment Strategists and CSEs to deliver AI agents that set the standard for innovation and reliability in healthcare.

• Cutting-Edge AI Innovation:
  You design sophisticated AI solutions using advanced LLM techniques (multi-turn reasoning, complex RAG, LLM-as-judge); solve novel healthcare AI challenges that move the category forward

• Proactive Problem-Solving:
  You identify customer issues early through deep monitoring and proactive communication, often solving problems before they impact clinical operations

• Advanced System Design:
  You architect complex AI systems with sophisticated RAG pipelines, nuanced tool-calling strategies, and advanced LLM techniques that solve novel customer problems

• Production Excellence:
  You own production reliability across multiple deployments, anticipate failure modes, implement proactive monitoring, and drive continuous reliability improvements

• Technical Leadership:
  You serve as the technical authority for complex, novel deployments; guide architectural decisions; mentor other engineers on AI techniques

• Customer Technical Partnership:
  You partner with sophisticated customer IT teams on complex challenges, explaining architectural choices, and collaborating on optimizations

• AI Innovation & Architecture – Design cutting-edge AI solutions to novel healthcare challenges; architect advanced RAG, tool-calling, and LLM technique approaches

• Advanced RAG System Design – Design and implement advanced retrieval-augmented generation systems; optimize for relevance, latency, and cost; handle complex data sources and sophisticated chunking strategies

• Advanced LLM Techniques – Apply sophisticated LLM engineering patterns (LLM-as-judge, multi-turn reasoning, complex prompt engineering); optimize agent behavior for production reliability

• Proactive Customer Problem-Solving – Anticipate customer issues; propose proactive AI-driven solutions; identify optimization opportunities

• Production Architecture & Operations – Design infrastructure for high-reliability AI systems; implement comprehensive monitoring, logging, and incident response; ensure systems meet production standards

• Complex Deployments – Lead technical execution for sophisticated, novel deployments; own integration architecture; solve complex AI challenges creatively

• Team Mentoring & Technical Leadership – Mentor junior FDEs on AI development and production patterns; contribute to technical standards and best practices

• 5-7 years of software engineering experience with expert-level Python and production software systems expertise

• Advanced hands-on experience with LLM frameworks (Lang Chain, Lang Smith); deep understanding of RAG, tool calling, and advanced LLM patterns; experience solving novel AI problems

• Proven ability to architect and implement complex AI systems; experience designing systems for reliability and scale

• Experience with sophisticated integrations and enterprise systems; strong understanding of systems reliability, error handling, and operational patterns.

• Bachelor's degree in Computer Science or related field from a top ranked university.

• Experience designing and optimizing advanced RAG systems at scale; deep knowledge of retrieval strategies, embedding…