Staff AI Engineer

We celebrate diversity and encourage individuals of all genders (m/f/d) to apply.

We’re on the lookout for an ambitious AI-Engineer to join our Engineering team at our office in Berlin. Join us in building the largest AI enabled fintech for healthcare!

As part of our freshly launched AI division at Nelly, where you'll be one of the pioneers shaping our future in AI. In a small, agile team, you'll work on developing cutting-edge AI systems and robust data pipelines—from rapid prototypes to scalable production solutions. This role is ideal for someone who combines deep ML theory with practical cloud and data engineering know-how, and who can drive innovative GenAI initiatives while keeping a pragmatic product focus.

About Nelly

We are a Tech Company and we believe healthcare should feel a lot less like paperwork… and a lot more like people. So we’re building the technology that lets medical practices run smoothly, simply, and without all the admin chaos that slows everyone down.

Our platform turns messy processes into smart, automated workflows, from patient journeys to billing to next-generation payments. Powered by AI, built for real humans, and designed to give medical teams the time and headspace they desperately need.

Why? Because Europe is facing a massive shortage of medical assistants. And if we don’t rethink how practices operate, the system won’t be able to keep up. We’re here to fix that, not with band-aids, but with real transformation.

We’re backed by €50M in Series B funding from world-class investors and are scaling fast to build Europe’s leading healthcare fintech. Our vision: empower over a million medical practices and make life better for millions of patients.

But here's the part we’re proudest of: we only work with nice people. It’s our number-one rule. No egos, no drama, no jerks. Just kind, curious, hardworking humans building something meaningful together.

If that sounds like your kind of place — welcome to Nelly.

Joining us, you will

• embrace a fast-paced, agile environment where outcome and quick progress is achieved through experimentation and rapid iteration.

• architect and lead the development of backend-first agentic services combining LLM services with tool use/retrieval, ReAct and Knowledge Graphs - defining technical strategy, standards, and best practices across the AI division.

• design and evolve our retrieval & knowledge infrastructure (embeddings, vector stores, metadata schemas, glossary, memories) ensuring accuracy, performance, and scalability across diverse use cases.

• define and champion production excellence: establishing standards for tracing, observability, reliability patterns, prompt/version control, experimentation frameworks, and deployment strategies.

• mentor engineers, conduct technical reviews, and elevate the team's capabilities through knowledge sharing and best practices.

• drive technical discovery, evaluate emerging AI technologies, and make strategic build vs. buy decisions.

• partner closely with product and business stakeholders to translate complex technical considerations into product strategy and roadmap decisions.

What you'll bring

• technical leadership mindset with high agency and proactive drive—obsessed with building world-class systems and enabling teams to ship exceptional user experiences.

• 8+ years building and operating backend systems in production (strong Python skills required - ideal as well: TypeScript for integration work), with 3+ years shipping LLM/GenAI features to users (RAG, tool use, planning, agent frameworks e.g MCP, multi-agent systems).

• strong ML fundamentals with hands-on experience in model evaluation, self-evolving agents (e.g Memory).

• deep expertise in distributed systems design: API architecture, data modeling, high-throughput async systems, event-driven architectures, caching strategies, and performance optimization.

• advanced retrieval engineering experience: embeddings, sophisticated chunking strategies, hybrid search algorithms, schema/metadata design, knowledge graphs, comprehensive eval frameworks, and production monitoring.

• proven track record of technical leadership: driving architecture decisions, mentoring engineers, and establishing engineering best practices.

• experience with cloud native development at scale, ideally AWS, but GCP is a strong plus, too.

• excellent communication skills in English with ability to articulate complex technical concepts to diverse audiences.

• Bonus skills:

• Experience with modern data workflow orchestration frameworks such as Dagster, Airflow, or Prefect, with emphasis on building robust, dependency-aware pipelines at scale.

• Track record of technical writing, open-source contributions, or speaking at industry events.

• Fluent German is a big plus, to improve the interaction between you and our user base.

What we offer

• Move your way: BVG ticket or a Swapfiets membership to cruise through the city

• Stay active: Urban Sports membership to sweat, stretch, or sauna your way through the week

• Gear up: Top-of-the-line equipment that actually makes work feel smooth

• Work your style: Flexible hours and a hybrid setup in the heart of Berlin-Mitte

• Change of scenery? Enjoy up to 4 weeks of workation wherever inspiration hits

• Grow fast: A dynamic environment, a steep learning curve, and endless opportunities to level up

• Join the ride: Be part of an AI-powered fintech that’s shaking up the German healthcare market

• Own it: Real responsibility, independent work, and plenty of freedom to make an impact

• Office vibes: A cozy, dog-friendly office where good vibes are basically mandatory

• Snack heaven: A fridge full of cold drinks and snacks waiting to be claimed

We celebrate diversity and welcome individuals of all genders (m/f/d) to apply — and because we know confidence gaps and impostor syndrome can get in the way, please don’t hesitate even if you don’t meet every single criterion; if you’re exceptional, tell us why, and we’d genuinely love to hear from you.