Albatross
At Albatross, we're building the second pillar of AI: a perception layer that understands how users actually experience content, in real time. Trained on live user interactions, Albatross learns and reasons on the fly. Our technology powers real-time, in-session discovery by adapting to evolving user interests, in real-time. We have raised significant funding and our platform already operates at scale, with billions of events being processed and hundreds of millions of predictions served.
The Role
As a Data Scientist, you will design and deploy machine learning models that power real-time personalization for our customers. You will own defined workstreams of ML projects end-to-end, and you will work closely with Applied Scientists and Engineers to translate product and customer needs into scalable ML solutions. More specifically, you will:
- Design and implement machine learning models for ranking, recommendation, and personalization
- Define feature engineering pipelines and modeling strategies for customer use cases
- Train, evaluate, and deploy models using our internal ML tooling and infrastructure
- Own project workstreams from data preparation through production deployment
- Collaborate with Applied Scientists to integrate new algorithms into production systems
- Contribute improvements to internal ML tooling and experimentation infrastructure
- Monitor model performance and iterate based on real-world feedback
Requirements
- Bachelor's degree in Machine Learning or STEM
- Strong background in machine learning, statistics, or data science
- Solid programming skills in Python
- Experience training and deploying ML models in production environments
- Familiarity with ML frameworks such as PyTorch, TensorFlow, or JAX
- Experience working with large-scale datasets and feature engineering pipelines
- Ability to work independently on moderately complex ML problems
- Strong communication skills in English
Nice to Have
- Experience with recommender systems, ranking models, or search
- Experience with large-scale experimentation and evaluation pipelines
- Familiarity with learning-to-rank models, bandits, or reinforcement learning
- Experience working with cloud environments such as AWS, GCP, or Azure
Benefits
- Flexibility to work from anywhere across Europe
- Budget for learning and training, attend events and conferences
