Vestiaire collective

Staff Data Scientist

Berlin Full Time
Vestiaire Collective is the leading global online marketplace for desirable pre-loved fashion. Our mission is to transform the fashion industry for a more sustainable future by empowering our community to promote the circular fashion movement. Vestiaire was founded in 2009 and is headquartered in Paris with offices in London, Berlin, New York, Singapore, Ho Chi Minh and Hong Kong and warehouses in Tourcoing (France), Crawley (UK), Hong Kong and New York.

We currently have a diverse global team of 700 employees representing more than 50 nationalities. Our values are Activism, Transparency, Dedication and Greatness and Collective. We are proud to be a BCorp.

About the role

We are seeking a highly skilled and experienced Staff Data Scientist to join our Operations and Customer Service department. You will be instrumental in developing advanced AI models that enhance both internal operational workflows and customer-facing experiences. This includes building systems that help our Curation team verify product quality and authenticity from customer-provided descriptions and images, as well as exploring and delivering new models aimed at improving how customers interact with our platform. The role requires strong end-to-end machine learning expertise and a user-centric mindset to drive measurable improvements in accuracy, operational efficiency, and overall customer experience.

What you will do

- Design and own end-to-end AI/ML solutions for item quality and authenticity detection, spanning:Image analysis (detecting marks, defects, wear, size inconsistencies).
- T ext and metadata understanding (brand, sizing, category anomalies).
- Counterfeit and fraud detection modelsDesign, prototype, and iterate on AI models that directly power and improve customer-facing experiences on our platform (e.g., smarter assistance).
- Collaborate closely with the Product and Curation teams to define requirements, integrate AI models into their workflow, and provide insights to enhance their verification processes.
- Advise and direct data/feedback collection for continuous improvement and monitoring of the performance of the models.
- Perform rigorous model evaluation, A/B testing, and continuous improvement of AI models.
- Work with engineering teams to ensure seamless deployment and integration of AI models into our existing platforms.
- Research and stay updated on the latest advancements in AI, machine learning, deep learning and computer vision to identify new opportunities and best practices.
- Mentor senior and mid-level data scientists, raising the technical bar on modeling, data quality, and experimentation best practices
- Communicate complex technical concepts and findings to both technical and non-technical stakeholders.

Who you are 
- 6+ years of experience in data science, machine learning engineering, or AI development, with a strong focus on computer vision applications and customer facing models.
- Deep expertise in applied AI/ML (computer vision, anomaly detection, fraud/risk modeling).Track record of leading technical initiatives and influencing decisions across teams.
- Experience in architecturing, deploying, and maintaining AI systems at scale.
- Proficiency in programming languages such as Python and experience with relevant libraries/frameworks (e.g., TensorFlow, TorchServe, TensorflowServing, PyTorch, scikit-learn, spaCy, Hugging Face Transformers, OpenCV).
- Deep understanding of machine learning algorithms, statistical modeling, and data manipulation techniques.
- Experience with data visualization tools and communicating insights effectively.
- Strong problem-solving skills, with the ability to tackle complex, ambiguous problems.
- Ability to work independently and collaboratively in a fast-paced, global team environment.
- Experience with cloud platforms (e.g., AWS, GCP, Azure) and MLOps practices is a plus.
- Experience building or maintaining customer service chatbot systems is a plus.
- Familiarity with database technologies (SQL, NoSQL) and cloud data warehouse (BigQuery/Snowflake)
- Excellent communication and interpersonal skills.
- Fluency in written and spoken English (please send your application in ENGLISH only)

Our Tech Stacks includes 
Deep Learning & ML frameworks & Libraries: PyTorch, Tensorflow, Scikit-learn, OpenCV, TorchServe, TensorflowServing
Model serving: Airflow, Torchserve, TFServing, Triton Inference Server,  REST APIs, gRPC
Deployment: K8s