Forward Deployed Engineer

AI Chopping Block; Northern (KY); Hybrid; USD 140,000 - 190,000; Full time

Job summary

Hippocratic AI in the United States is seeking a Forward Deployed Engineer to own AI deployments end-to-end, from design to production. You will work closely with Deployment Strategists and customers to build reliable systems that operate within healthcare environments.

You'll apply LangChain, LangSmith, and RAG-based techniques, build integrations to EHRs and data warehouses, and own incident response and production monitoring.

Qualifications

• 3–5 years of software engineering experience with production systems
• Strong Python fundamentals and experience with AI frameworks
• Deep understanding of RAG, tool calling, and LLM-based decisioning

Responsibilities

• Identify customer challenges and design AI solutions using LLM techniques
• Design retrieval-augmented generation pipelines grounded in customer data
• Implement tool-calling architectures and MCP connections
• Develop production Python code with LangChain and LangSmith
• Set up secure, monitored production environments and deployments
• Monitor and support deployed systems, respond to incidents with customers

Skills

Python

LangChain

LangSmith

RAG

Tool calling

LLM-as-judge

Education

Bachelor's degree in Computer Science or related field

Tools

LangChain

LangSmith

APIs

Databases

Job description

Forward Deployed Engineer (FDE)

The Forward Deployed Engineer is the technical owner for AI deployments. You will be a core contributor to our agentic AI platform. This is a high-ownership role where you work closely with Deployment Strategists and customers, building real production systems that directly impact healthcare operations. You need to be a strong software engineer who enjoys working in customer environments and taking ownership of end-to-end system reliability.

You have expertise in software development in python, experience with frameworks such as langchain and langsmith, deep understanding of LLM techniques such as RAG, LLM as a judge, and MCP/tool calling.

What Success Looks Like

• AI Innovation: You use your expertise in AI Engineering to solve cutting-edge problems in healthcare-focused conversational AI, applying RAG, tool-calling, and advanced LLM techniques to novel customer challenges

• Customer Problem-Solving: You identify issues early through close monitoring and proactive communication, often solving problems before they affect clinical operations

• Reliable AI Systems: You build integrations that connect reliably to customer systems (EHRs, data warehouses, operational tools), handling errors gracefully and monitoring for anomalies

• Smooth Deployments: You execute deployment plans without surprises—infrastructure is ready, integrations are tested, cutover is planned and executed professionally

• Production Ownership: You monitor deployed systems, respond quickly to incidents, and drive operational improvements that keep agents running smoothly

• Technical Partnership: You help customers understand the AI system architecture, debug issues collaboratively, and build their confidence in the solution

Core Responsibilities

• AI Innovation & Problem-Solving – Identify customer challenges and design AI solutions using advanced LLM techniques (RAG, tool calling, LLM-as-judge); implement novel approaches to healthcare AI problems

• RAG Pipeline Implementation – Design and implement retrieval-augmented generation pipelines that ground LLM responses in customer data, ensuring accuracy and clinical relevance

• Tool & MCP Architecture – Implement tool-calling architectures and Model Context Protocol (MCP) connections that enable agents to interact with customer systems safely

• Python AI Development – Build production Python code using LangChain, LangSmith, and modern AI frameworks to create reliable AI systems

• Infrastructure & Deployment – Set up secure, monitored production environments; manage deployment and go-live activities

• Production Monitoring & Support – Monitor deployed systems, respond to incidents, troubleshoot problems with customers, implement fixes

What You Bring

Must Haves

• 3-5 years of software engineering experience with strong Python fundamentals and production software development experience

• Hands-on experience with LLM frameworks (LangChain, LangSmith) and understanding of modern LLM development patterns

• Deep understanding of LLM techniques: RAG, prompt engineering, tool calling, LLM-as-judge, and related patterns

• Experience building integrations with APIs, databases, or enterprise systems; comfort with async patterns and error handling

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

Nice to Haves

• Experience with Model Context Protocol (MCP) or similar approaches for tool integration

• Healthcare IT experience (EHR integrations, FHIR, HL7, healthcare data standards)

• Production DevOps or infrastructure experience; ability to set up monitoring and incident response

• Experience deploying AI systems or working with LLMs in production environments

Why Hippocratic AI

• You're innovating in AI-native healthcare. You're not building traditional integrations—you're solving cutting-edge problems in conversational AI for healthcare. Every RAG pipeline you design, every tool-calling pattern you implement, every LLM optimization you discover contributes to healthcare transformation.

• You work with world-class AI engineers and clinical experts from Google, Meta, Microsoft, NVIDIA, Johns Hopkins, Washington University, Stanford. You'll tackle harder AI problems alongside smarter people. You'll grow your AI expertise faster here than almost anywhere.

• Backed by $404M from top-tier AI and healthcare investors—CapitalG, a16z, General Catalyst, Kleiner Perkins, plus strategic health system investors. This validates the category and gives you the resources to focus on innovation without runway concerns.

• This is category creation. You're defining how LLM agents interact with healthcare systems, how RAG grounds clinical AI, how to deploy AI safely at scale. You're not following playbooks—you're writing them..