AI Engineer

Company DescriptionLioByte Technologies builds AI systems and ships them into production for business clients.Role DescriptionWe need an expert in recommendation systems to design and ship our recommendation engine. You will own the work from the first data review to a live system that real users see. This is a 3 to 6 month consulting contract. If the work and the fit are strong, we will offer you a full time role.You will use Claude Code every day to build faster, and you will review everything it writes.SkillsRecommender Systems, Machine Learning, Python, Learning to Rank, Vector Search, SQL, Claude CodeWhat you will doReview our data and pick the right recommendation approachDesign and build candidate generation and rankingBuild a simple baseline first, then improve on it with proofSet up offline metrics and live A/B tests so we know what worksHandle the cold start problem for new users and new itemsServe recommendations through fast, reliable APIsDocument your work and teach our team how to run and extend itTop 5 technical skills we look forRecommendation algorithms: collaborative filtering, content based methods and hybrid approachesRanking and learning to rankEmbeddings and vector searchPython and machine learning libraries (PyTorch, TensorFlow or scikit-learn)SQL, data pipelines and experiment design (A/B testing)Must have3+ years of experience in machine learning or software engineeringProven experience shipping a recommendation or personalization system to productionHands on experience with Claude CodeStrong Python and SQLClear thinking about metrics, such as precision, recall, NDCG and click through rateAble to work on your own and explain your decisions in plain languageNice to haveExperience with search systems such as Elasticsearch or SolrExperience with large language models for recommendations or rerankingExperience with real time features and cachingHow to applyApply on LinkedIn, or email your resume to hello@liobyte.com. Include a short note on the best recommendation system you shipped. Tell us what you built, what it moved and what you would do differently.