I
$100,000 – $125,000
Listed on impact.com’s own careers site. You apply with them directly — we never stand between you and the employer.
What this role is
This role builds machine learning systems that recommend partnerships, products, and creators across impact.com's network of advertisers, publishers, and consumers. It suits experienced data scientists who can own projects end-to-end—from problem definition through production deployment—and who want to apply graph neural networks and embeddings to a real-world, multi-entity recommendation problem at scale.
Our summary, not impact.com’s wording. The full posting is on their site.
Skills this role names
Log in to see which of these are already on your profile.
What they ask for
Required
- 3+ years of data science or applied ML with shipped production models
- Python and SQL proficiency
- Experience with large-scale data and distributed compute (Spark, Databricks, or equivalent)
- Hands-on experience building recommendation or ranking systems
- Experience with embeddings and representation learning
- ML engineering capability to build and maintain production pipelines
- Strong experimentation and A/B testing skills
- Active use of AI coding agents in day-to-day work
Nice to have
- Graph-based ML experience (graph neural networks, graph-aware retrieval, knowledge graph embeddings)
- Modern deep learning recommender architectures (two-tower, sequence/transformer-based models)
- Vector search and vector database experience
- Real-time ML serving and feature store familiarity
- Contextual bandits, reinforcement learning, or off-policy evaluation experience
- PyTorch/TensorFlow and PyTorch Geometric or DGL proficiency
- GCP experience and mature MLOps practices
- Background in adtech, martech, e-commerce, or marketplace recommendations