Requirements: English
Company: CurveCatch
Region: Antwerpen , Flanders
Are you an AI aficionado with a passion for building models that make a real-world impact? Do you dream in Python and get excited by large, clean datasets? Forget needing 100 years of experience, we''re looking for a brilliant Machine Learning Engineer ready for a new adventure at a fast-paced, mission-driven startup! If you love tackling complex problems & working with real-world datasets, owning the ML lifecycle, and working with a unique, energetic team, keep reading!
ABOUT CURVECATCH
CurveCatch is a Belgian venture-backed startup revolutionising the way people shop for intimate apparel. Were a bra shopping companion that uses AI to help shoppers find the perfect bra. We offer a home-try-on service where shoppers fill out a questionnaire and get 8 items across brands to try on at home. We started from the local specialty shops of founder Kimias parents during Covid. Since then, were a team of 7, have raised just under 1 million in pre-seed funding from strategic angels, accelerator XX in San Francisco, an innovation grant, and a grant from Y Combinator. We''re now a 7-figure business.
Never thought your next adventure would be in the lingerie sector? Stick around and find out!
WHAT WILL YOU DO?
As our Machine Learning Engineer, you''ll be pivotal in developing and deploying the AI that powers CurveCatch''s personalization magic. You''ll work across the ML lifecycle to deliver impactful models and shape our AI strategy. Your responsibilities will likely include:
- Designing, developing, training, and deploying machine learning/deep learning(DL) models to enhance product personalization (style, shape, size) and recommendation systems.
- Researching and implementing novel ML and/or deep learning techniques and algorithms suitable for our unique lingerie domain datasets.
- Managing and improving the end-to-end ML workflow, including data preparation, feature engineering, model training, validation, deployment, and monitoring in production.
- Optimizing ML/DL models and infrastructure for performance, scalability, and cost-effectiveness (leveraging tools like AWS Sagemaker, Metaflow, W&B and making smart use of cloud credits).
- Collaborating closely with the CTO (Nils) on the AI/R&D roadmap, data strategy, and continuous improvement of our MLOps processes and lean ML toolstack (DBT, Snowflake, Metaflow, AWS Sagemaker, PyTorch, Metabase, Hex, W&B, etc.).
- Working with our full-stack engineer (Denis) on infrastructure decisions impacting data and AI systems.
- Providing input on product features related to ML/DL models and data collection, championing data quality ("garbage in, garbage out").
- Actively seeking and implementing ways to automate and streamline ML/DL processes to maximize time spent on ML/DL modelling itself and impact.
MUST-HAVE QUALIFICATIONS
- Proven 5 years+ of relevant industry experience designing, building, training, and deploying machine learning/deep learning models in a production environment.
- Strong theoretical understanding and practical application of ML/DL fundamentals (algorithms, evaluation, statistics, feature engineering).
- Strong proficiency in Python and common ML libraries/frameworks (e.g., Pandas, Scikit-learn, PyTorch, ..).
- You have a degree (Bachelor''s, Master''s or PhD) in a quantitative field such as Data Science, Computer Science, Artificial Intelligence, Statistics, Mathematics or related discipline.
- Hands-on experience with deploying ML systems in the cloud at least 1 major cloud platform (AWS preferred, GCP useful) and familiarity with MLOps principles and tools (e.g., Metaflow, W&B, Sagemaker, or similar).
- A pragmatic approach focused on delivering impactful ML solutions efficiently in a small team ("garbage in, garbage out" mindset, passion for automation).
- Excellent problem-solving skills and the ability to independently drive research and development projects.
- Strong communication skills in English.
NICE-TO-HAVE QUALIFICATIONS
- Hands-on experience with personalization models or recommendation systems in production.
- Hands-on experience with integrating LLMs and fine-tuning GenAI models on customer datasets in production.
- Experience working in an e-commerce environment and building ML/DL models for e-commerce use-cases.
- Experience working in a start-up environment.
- Proficient in SQL and experience with data engineering and data warehousing concepts (experience with tools like DBT, Snowflake is a plus).
- Experience with any of our specific stack tools (DBT, Snowflake, Metaflow, W&B, Sagemaker, Hex, Metabase).
- Experience mentoring junior data professionals or interns.
WHY IS YOUR ROLE CRUCIAL FOR US?
Your work