About the job

👋 Welcome to dexter health!

At dexter health, we build AI-powered software for care teams. Our mission is to reduce administrative workload in healthcare so caregivers can spend more time with patients.

We are looking for a high-agency AI Engineer to help us build new AI features faster and improve the quality, reliability, and speed of existing AI workflows.

This is a hands-on engineering role. Not research. Not prompt-only. You will turn ambiguous product ideas into working, production-ready AI features.

The role is mostly focused on shipping AI product features, with some AI systems and infrastructure work where needed.

You will work closely with product and engineering, but we expect you to take real ownership. You should be comfortable moving fast, making technical decisions under ambiguity, and using AI development tools such as Claude Code, Codex, Cursor, Copilot, or similar every day.

Tasks

As our AI Engineer, you will:

Build new AI-powered product features from idea to production
Improve existing AI workflows for quality, reliability, latency, and user value
Design and implement LLM-based workflows, structured outputs, validation logic, and fallback behavior
Build evaluation loops, tests, and quality checks for AI-generated outputs
Integrate AI capabilities into existing product and backend systems
Work with commercial and open-source LLMs without being tied to one specific provider
Support self-hosted model workflows where they make sense for quality, speed, cost, or control
Debug AI feature failures across inputs, outputs, data, backend logic, and user flows
Use AI development tools as a core part of your daily workflow
Ship quickly while keeping production quality high

Requirements

We care less about formal seniority and more about speed, intelligence, ownership, and product impact. We like people who operate with founder-like urgency: they figure things out, make progress under ambiguity, and care about outcomes more than titles.

Must-have

Strong software engineering skills, especially in Python or a comparable backend language
Experience building AI-powered product features or LLM-based workflows
Ability to turn ambiguous product ideas into working software quickly
Strong understanding of how to design, test, validate, and improve AI outputs
Experience integrating AI workflows into production systems
Strong debugging instincts across application logic, data, model outputs, and user-facing behavior
Experience with evaluation, testing, validation, or quality checks for AI-generated outputs
Serious experience using AI development tools such as Claude Code, Codex, Cursor, Copilot, or similar as part of your daily workflow
High intelligence, fast learning speed, bias to action, and ownership mindset
Comfortable with ambiguity, fast decisions, and a high-trust startup environment
Clear written and spoken English

Nice-to-have

Experience with frontend or fullstack product development
Experience with self-hosted LLMs, model serving, inference optimization, or similar systems
Experience with open-source LLMs and related deployment workflows
Experience improving latency, cost, quality, or reliability of AI systems
Experience with healthcare software, healthcare data, or regulated environments
Experience working with structured data extraction, documentation automation, voice workflows, or workflow automation
German language skills
Knowledge of nursing homes or elderly care workflows

This role is probably not for you if

You are mainly looking for an ML research role
You are a prompt engineer without strong coding skills
You need detailed specifications before making progress
You prefer slow, highly structured corporate environments
You are mainly looking for management, not hands-on building
You want to use AI tools only occasionally instead of as part of your daily workflow
You optimize for perfect process over fast, reliable execution

Benefits

Remote work
Fair compensation based on skills, experience, and location
Ownership of important backend systems
Work on software used in real healthcare workflows
Modern AI-native development workflow
Room to grow with the company

Why?

Caregivers spend too much time on documentation, coordination, and administrative work. We build technology that reduces this burden.

AI is core to our product. But useful AI features do not come from demos alone. They need strong engineering, fast iteration, evaluation, production thinking, and deep ownership of the user outcome.

If you want to build AI product features that ship, improve real workflows, use AI tools every day, and take ownership in a fast-moving team, we would like to hear from you.

Responsibilities

AI and Generative AI Engineer with over two years of experience designing, building, and deploying production-grade Large Language Model systems, AI agents, and Retrieval-Augmented Generation pipelines. Skilled in LangChain, LangGraph, Hugging Face, FastAPI, and multi-agent architectures, having delivered 4+ production applications while reducing AI workflow latency by approximately 30 percent and improving accuracy by approximately 35 percent. Brings strong enterprise engineering discipline from Accenture, having supported 25 or more projects with up to 80 percent process automation, combined with a solid foundation in deep learning, vector search, and cloud-based deployment. Holds a Master of Science in Applied Artificial Intelligence from Cranfield University, United Kingdom, and is available to join immediately.