Job Summary:
Onescreen is a modern platform for out-of-home advertising, focused on streamlining the planning, buying, and measuring of OOH campaigns. They are seeking a Founding Machine Learning Engineer to own the development of matching algorithms and the data platform that supports them, along with designing and shipping models that optimize OOH inventory rankings.
Responsibilities:
โข Design and ship matching and ranking models for OOH inventory: candidate generation, re-ranking, geospatial-aware scoring.
โข Own the data warehouse layer end to end: staging, marts, feature pipelines, freshness, lineage.
โข Stand up offline and online evaluation infrastructure โ measure the gap between them, don't assume it.
โข Publish ranking and matching APIs for product surfaces, with latency and quality SLOs.
โข Instrument model monitoring: drift detection, prediction distribution, feature freshness, retraining triggers.
Qualifications:
Required:
โข you have owned a production ranking, matching, or recommendation system end-to-end
โข Strong production Python (NumPy, Pandas, FastAPI, SQLAlchemy)
โข Strong SQL and modern data warehouse experience (BigQuery preferred)
โข Real ranking and matching modeling fluency โ learning-to-rank, retrieval and re-rank patterns, not just classification
โข Evaluation methodology rigor: holdouts, leakage prevention, online vs. offline gap measurement
โข Comfort owning the data pipeline as well as the model
โข Bias toward shipping. Clear writer. Self-directed.
Preferred:
โข Geospatial data experience (H3, PostGIS, GeoPandas)
โข Mobility or location data experience
โข Embedding-based retrieval (pgvector, FAISS, vector databases)
โข Bandits, contextual bandits, or online learning
โข A/B testing infrastructure design
โข Causal inference
โข dbt
โข Ad-tech or OOH domain familiarity
Company:
Onescreen is the modern partner for out-of-home advertising. Founded in 2020, the company is headquartered in Boston, USA, with a team of 51-200 employees. The company is currently Growth Stage.