We’re looking for an engineer who builds AI systems that create real impact in production (not just demos) and has worked with retrieval or agent-based approaches on enterprise data.
At Natuvion, we move business-critical data and processes between platforms. This data enables powerful AI — but also comes with complexity, sensitivity, and high stakes. We use AI to automate internal processes and to build intelligent features into our products, and you’ll work across both areas.
We operate with strictly protected data that is never exposed to external LLMs, supported by a strong authorization model. Self-hosted models are an important part of our strategy.
Our core stack is built in Go with gRPC-based services, including a custom AI router. While AI work may start in Python, production services are built in Go — and you’ll own them end-to-end.
We deliberately stay flexible with our AI stack. The field evolves quickly, and we value engineers who stay current, think critically, and bring ideas to the table.
This role focuses on building robust, production-grade systems designed to be operated, evaluated, and improved over time. We’re looking for someone who prioritizes maintainability, thoughtful evaluation, and chooses the right tool for the job.
If that excites you, we’d love to hear from you.
Your Responsibilities:
Design, build, and operate RAG solutions across the full spectrum — from semantic search through to retrieval over highly structured data and knowledge graphs
Build agentic systems that perform multi-step tasks reliably and safely against enterprise data
Drive automation of internal processes with AI, and ship AI features into customer-facing products
Own retrieval quality end to end: chunking and embedding strategies, hybrid and re-ranking approaches, and the evaluation that proves it works
Evaluate and recommend the tooling for our AI stack — vector stores, orchestration, retrieval frameworks, model choices — and drive those decisions together with our architect. We expect informed proposals, not a wait for instructions
Author production services in Go (gRPC) and integrate them with our AI router and existing platform; prototype and iterate in Python
Make grounded technical decisions — retrieval vs. fine-tuning vs. prompting vs. a classical approach — and defend the trade-offs in architectural reviews
Requirements
You hold a degree in Business Informatics or Computer Science
You have several years of experience, a strong Python proficiency for AI development, and genuine comfort working in Go — you're 100% willing and able to author production gRPC services, not just call them
A proven track record of building AI features on enterprise data that actually shipped and stayed in production
Real understanding of the fundamentals behind modern RAG: embeddings and vector similarity, retrieval and ranking, and how transformer-based models behave. You reason about why a pipeline succeeds or fails — you don't guess
Hands-on experience designing and evaluating retrieval and agentic systems, including building your own metrics and eval rather than trusting vibes
Experience with knowledge graphs or structured/semantic data representations is a strong plus
Curiosity that shows: ideally you've fine-tuned a small model yourself (LoRA / QLoRA or similar) and understand the basics of what's happening under the hood
You stay genuinely current in a fast-moving field and hold reasoned opinions. You can walk into a discussion with our architect with a concrete recommendation and defend the trade-offs — and change your mind when the evidence says so
Comfortable in cloud-native environments — you think about observability, failure modes, and cost as first-class concerns
Professional working proficiency in English — you can explain complex technical ideas clearly to peers and stakeholders
If you think that you don't meet all the requirements: With us, there are "no limits" to your development! Go your way with us - we support you! Just show us who you are.
What you can expect from us:
An environment that is always open to change and optimization. There is no "it's always been like this" with us. You have the opportunity to contribute your knowledge, design processes, standardize existing topics or optimize workflows. Be a source of inspiration and bring us even further forward with your expertise!
We create conditions in which you feel comfortable:
Home office contracts & absolute flexibility through free organization of working hours
Permanent position and 30 days of vacation
FlexWork: Work remotely from other European countries for up to 3 months per year
Monthly budget for individually selectable benefits from over 50 possible offers via emplu, various offers via corporate benefits, as well as bicycle and car leasing via salary conversion
Mental Health Benefit 'Nilo' – 10 free sessions with psychologists annually as well as access to meditations and courses
We provide you with targeted support in your professional and personal development at Natuvion
Mentoring program for a structured and personal induction
Be part of the #teamgreen - At Natuvion, you'll work on innovative projects as part of a team that stands up for each other. We rely on cooperation, openness and trust
Modern equipment and central offices in Walldorf, Berlin, Munich and Leipzig
Your long-term perspective is important to us, which is why we subsidize your company pension scheme as well as capital-forming benefits
Join #teamgreen - Natuvion is a digital moving company.
Our team does not move tables, filing cabinets or chairs. Natuvion transports business-critical data and processes from one technology platform to another. Typical Natuvion "relocation services" include data migration, data transformation, data integration, data privacy, data security, and data quality.
Our >400 consultants and developers in Germany, Austria, Slovakia, the USA and Australia have extensive know-how in (SAP)® projects and a profound understanding of processes across industry boundaries. With a lot of experience, commitment and commitment, they support our customers with advice, services and their own software technology. In this way, we enable companies to always use their data and processes on the most modern and innovative platforms.
Originally posted on