.Valispace is a productivity software and a single source of truth for all of the ''loose'' engineering data of hardware projects, helping engineers streamline efforts from concept to test and escape from document hell! We have one simple mission: to empower engineers to faster craft the complex products that help propel humanity forward.We are a diverse, kind, curious and ambitious team and take pride in working closely with companies that are building futuristic ideas that seem like magic to us today. That's right, our users are taking people to space, building flying cars and much more!If you like the idea of working in an environment that encourages creative and autonomous work, focuses on your growth potential and where there's always room to discuss the quirks of living on this planet, then we might just be a perfect fit.We are looking for an Applied LLM Developer to join our team and be at the forefront of LLM techniques, making an immediate impact in this dynamic field.About the role Join product discovery calls with customers and our solution team to understand in depth the problem engineers are trying to solveIdeate potential solutions based on LLMs and discuss its integration to the product together with Valispace's UX, backend and product teamsMake prototypes that quickly prove the feasibility of solutions, using commercially available APIs and/or local LLM modelsOptimize prototypical solutions by getting them production-ready through prompt engineering, finetuning, etc.Assist the Valispace backend and dev-ops teams in planning, implementing and deploying the solutionsDesign and develop tests that constantly assess the quality of LLM results in development and production environmentsWhat we're looking for In-depth hands-on experience in implementation of LLM techniques, such as prompt engineering, model finetuning and embeddings for commercial applicationsHands-on experience with using commercially available APIs (such as OpenAI's text generation, embeddings, function calling, finetuning, etc.) and fine tuning prompts for production grade resultsHands-on experience with running and fine tuning commercially available open source LLM models (e.G. Llama, Mistral, etc.), implementing and optimizing text embeddings (e.G. instructor, gte, jina, etc.) as well as using toolchains around them (e.G. Ollama, langchain, etc.)Interest in defining and implementing methods on monitoring of output qualityDesire to quickly and pragmatically bring value to users, iterate and then improveHigh curiosity to stay up to date with state of the art of this fast moving fieldInterest and/or experience in hardware engineering concepts such as requirements engineering and verification planningCompensation, benefits and perks Comprehensive health insurance; Nilo
