AI Engineer

Job Description

Job Description

WHO WE ARE

Emergency clinicians make critical decisions in seconds. Handtevy is the Clinical Intelligence platform built for those moments, trusted by EMS agencies and hospital emergency departments across all 50 states.

Handtevy is a healthcare technology company headquartered in South Florida. 3,000+ EMS agencies and hospitals in all 50 states and 200,000+ clinicians rely on the Handtevy platform to deliver safer, faster, and more consistent care.

THE OPPORTUNITY

We're expanding AI in our SaaS platform to assist clinical users in their work—surfacing the right information, accelerating workflows, and reducing manual effort for the teams who configure and manage clinical content. AI-generated outputs are designed to be grounded, traceable, and reviewed through appropriate clinical governance before they are used in customer-facing or safety-critical workflows. AI augments clinical teams; it does not replace their judgment.

We're looking for an AI Engineer who can design and ship AI capabilities that support clinical content, protocol management, administrative workflows, and clinically governed review processes within the SaaS platform. This is a hands-on, build-it engineering role for someone who has taken generative AI from prototype to production and knows how different those two things are.

You should be comfortable building with foundation models. We need someone who can turn today's best models into trustworthy, well-evaluated capabilities that hold up under clinical-expert review.

You'll work closely with backend engineers, engineering leads, Product, and clinical experts who validate what the system produces. AI-assisted development is already part of how this team works, and you'll help push that further.

WHAT YOU'LL DO

Build Agentic Workflows & LLM-Powered Features

• Design, build, and ship agentic systems and multi-step LLM orchestration using LangChain / LangGraph (or equivalent), including tool-calling, planning, and state management.
• Turn product problems into reliable AI capabilities that assist clinical users in the SaaS platform, owning them from prototype through production hardening.
• Build features so that outputs are surfaced for human clinical-expert review and validation, never as unchecked recommendations.
• Develop strong prompting, context-management, and tool-integration patterns that work consistently rather than only in the happy path.

Design & Operate RAG Pipelines

• Build and tune retrieval-augmented generation pipelines end to end: ingestion, chunking, embeddings, vector storage, retrieval strategy, and grounding.
• Make retrieval trustworthy and traceable on clinical and protocol content, so the experts validating each output can see what an answer is grounded in.
• Evaluate and improve retrieval quality with concrete metrics, not impressions.

Engineer Reliable Backend Services

• Build performant, well-tested Python services and APIs using FastAPI, integrating AI capabilities cleanly into our TypeScript-based platform.
• Design optimized data access across SQL and NoSQL stores and vector databases to support retrieval and agent workflows.
• Deploy and operate on AWS, with sound observability, logging, and cost awareness for LLM-heavy workloads.
• Champion code quality, security best practices, and comprehensive test coverage in line with the integrity our systems require.

Own Evaluation, Quality & Safety

• Build evaluation harnesses and guardrails so we can measure model and pipeline quality, catch regressions, and ship with confidence.
• Treat hallucination control, grounding, and traceability as first-class engineering concerns, and design every feature around a human clinical expert validating the output before it is trusted.
• Establish and evolve our standards for how AI features get tested, reviewed, monitored, and released.

Partner & Raise the Bar

• Partner with clinical experts to build the review and validation workflows that keep a human in the loop on every output.
• Participate in architecture discussions, code reviews, and sprint planning, and bring sound engineering judgment to a fast-moving space.
• Stay abreast of a rapidly changing landscape and help the team adopt what is genuinely useful while ignoring the hype.
• Mentor and level up the broader team's fluency with AI-assisted development and applied GenAI patterns.
  

YOUR ROLE ON THE TEAM

You're joining a lean, high-impact engineering organization. Our CTO sets the technical and AI vision. Our Director of Product owns the roadmap and the voice of the customer.

You'll be part of a team making applied AI real here. You and your fellow engineers take a hard product problem, decide whether an agent, a RAG pipeline, or something simpler is the right answer, build it well, and prove it works, always within a workflow where a human clinical expert validates the result before anyone relies on it. You'll have real autonomy and influence, and real accountability for the reliability of what you and the team build.

This is a role for someone who gets energy from shipping working systems, not demos, and from being rigorous because clinicians depend on what you build.

WHAT WE'RE LOOKING FOR

Must-Haves

• 5+ years of professional software engineering experience, with strong proficiency in Python and TypeScript.
• Hands-on experience building and shipping production LLM / generative AI applications, not just prototypes or notebooks.
• Demonstrated experience designing agentic workflows and multi-step LLM orchestration with LangChain / LangGraph or equivalent frameworks.
• Experience building RAG pipelines end to end: embeddings, vector stores, retrieval strategy, chunking, and grounding.
• Build well-tested AI services and APIs, primarily in Python and/or TypeScript, integrating cleanly with our TypeScript/NestJS platform. FastAPI experience is preferred.
• Experience building human-in-the-loop review or expert-validation workflows.
• Practical command of prompt engineering, context management, and LLM evaluation.
• Proficiency with relational and NoSQL databases (SQL: MySQL, optionally Postgres/MSSQL; NoSQL: MongoDB, optionally DynamoDB/Redis), and familiarity with vector databases (e.g., pgvector, OpenSearch, Pinecone).
• Experience with AWS services (e.g., S3, Lambda, CloudWatch, Aurora, Bedrock).
• Hands-on experience with Docker, Git, and CI/CD pipelines (e.g., GitHub Actions, Bitbucket Pipelines).
• Strong grasp of software design patterns, security best practices, and system architecture.
• Strong fluency with AI-assisted development tools such as Claude Code, GitHub Copilot, Cursor, or similar.
• Excellent collaboration and communication skills in a fast-paced, Agile environment.
• Bachelor's degree in Computer Science, Engineering, or a related field, or equivalent practical experience.
• Authorized to work in the United States.

Nice-to-Haves

• Experience with LLM observability and evaluation tooling (e.g., LangSmith, Langfuse, or similar).
• Experience with guardrails, content safety, or structured-output tooling.
• Background in healthcare, emergency services, or other regulated, safety-critical domains.
• Familiarity with NestJS.
• Knowledge of Datadog, New Relic, or similar observability platforms.
• Experience working in SOC 2 or similarly compliance-driven environments.

THE RIGHT FIT

• You ship working systems, not demos. You've carried an AI feature from prototype to production and you know how much harder the second half is.
• You're rigorous about evaluation. You don't trust an output because it sounds confident. You measure it, and you design for a human expert to validate it.
• You reach for the simplest thing that works. Sometimes that's an agent. Often it isn't, and you know the difference.
• You move fast with new tools but keep your judgment. The space changes quickly; you adopt what's real and skip the rest.
• You care about the mission. Our clinical experts stake their names on what this platform produces, and engineering that supports them deserves to be built that seriously.

BENEFITS

• Competitive salary commensurate with experience.
• Comprehensive health, dental, and vision coverage.
• 401(k).
• PTO.
• Paid holidays.
• Investment in professional development and modern engineering tools.
• Direct impact on a platform used in life-saving emergency care.
• Collaborative, mission-driven engineering environment.

HOW TO APPLY

Send us a brief intro and your resume. We're most interested in something real you've built: an agentic workflow or RAG system you took to production. Tell us what it did, what broke along the way, and most importantly, how you knew it was actually working.

*Compensation is competitive and commensurate with experience.*