AI Engineer, Retrieval & Quality

Job description

THE ROLE You will design and own the systems that decide which licensed data reaches our customers' models, and the evaluation infrastructure that proves it is better than the alternatives. You will work closely with our data scientists, who own research, methodology, and data quality. You own production retrieval and the eval infrastructure that runs on top of that. We are early enough that many of the core systems are still being defined. You will not be scaling someone else's architecture. WHAT YOU'LL DO - Design and operate the retrieval pipeline that serves licensed data to AI agents and models in real time: hybrid search, ranking, fusion, re-ranking. - Build the eval harness that runs continuously, gates deploys on quality, and surfaces regressions before customers feel them. - Translate research from our data science team into production systems, then own them end to end. - Define what good means for Redpine's output and build the dashboards that prove it across customers, verticals, and competitors. - Work across the stack as quality demands it, from ingestion signals through embedding pipelines to the API response. WHAT WE'RE LOOKING FOR - Production experience with retrieval systems: search, ranking, recommendation systems, or RAG at scale, not just notebooks. - Strong opinions on evaluation, both offline and online. You have designed test sets, run A/B experiments, and argued with data scientists and product managers about whether a metric reflects reality. - Comfortable with the full retrieval stack: embeddings, vector and lexical indexes, learning-to-rank, hybrid systems, and knowledge graphs. - Have shipped, not only researched. You know the difference between a method that works in a paper and one that works in production. - Comfort operating where direction evolves quickly and problems are not yet well-defined. - We work primarily in Go, Rust, and Python in a multi-cloud environment. We hire for judgment, not stack. WHY THIS ROLE Most retrieval and AI engineering roles are about plugging the latest models into an existing product. This isn't. You will be working on questions like: - How do you prove that licensed data produces better agent outputs than scraped data, with rigor that holds up to a customer's evaluation team? - What does a retrieval system look like when freshness, provenance, and rights are first-class signals alongside relevance? - How do you build evals that are honest enough to fail your own deploys and convincing enough to win customers? This role sits at the core of whether Redpine is differentiated infrastructure or a nicer API on commodity vector search. PRACTICAL DETAILS - Based at Redpine HQ in central Stockholm. Office-first, with real autonomy for deep-work days and life admin. - Requires a valid Swedish work permit or similar eligibility. Relocation support available. - Competitive salary and meaningful equity. - Small team, high ownership. The same people design, ship, and run the systems. ABOUT REDPINE If models were the first wave of AI, and compute the second, we are building the data layer that comes next. Only a small fraction of the world's data is on the open internet. The rest, high-quality, domain-specific, often critical, sits behind paywalls, in databases, or with rights holders. Redpine is building the infrastructure to unlock it. We provide AI builders and autonomous agents with access to licensed, high-quality, multimodal data through a unified platform and API. The goal is simple: make AI systems more accurate, more useful, and grounded in real-world information. You will work closely with the founding team, including Anders (ex-partner at VC, McKinsey) and David (ex-tech and product leader at Spotify, Zettle, and Lunar). We are backed by Nordic Ninja, Node VC, and Luminar, alongside angels from OpenAI, Spotify, and Perplexity. If you are eager to make a meaningful impact in the AI space, we would love to hear from you. We are committed to building a diverse and inclusive team. If you are excited about this role but your experience does not align perfectly with every qualification, we encourage you to apply anyway.