About the Role
Seeking a senior ML Encoder Lead to develop shared customer representations from longitudinal transaction, sales, and interaction data. The ideal candidate will independently define modeling objectives, build and evaluate encoder/embedding models, develop production-ready code, and determine whether the approach provides meaningful downstream value.
Responsibilities
- Define modeling objectives independently.
- Build and evaluate encoder/embedding models.
- Develop production-ready code.
- Determine if the approach provides meaningful downstream value.
Requirements
- Proven experience personally training encoder or embedding models and designing pretraining objectives.
- Deep expertise in representation learning, including self-supervised/contrastive learning, sequence/temporal modeling, transformers, GNNs, or recommender embeddings.
- Experience with large-scale, sparse, longitudinal event data such as transactions, clickstreams, customer journeys, or engagement histories.
- Experience developing inductive representations for entities with limited historical data.
- Strong model evaluation skills, including time-based splits, leakage detection, cold-start analysis, uncertainty, and robust baselines.
- Ability to evaluate embeddings for incremental signal, calibration, stability, drift, and subgroup performance.
- Strong Python skills with PyTorch or JAX, SQL, distributed data processing, and cloud-based model training.
- Experience taking ML models from research to production, including pipelines, data contracts, versioning, serving, monitoring, and reproducibility.
- Strong communication skills with the ability to present findings, uncertainty, and recommendations to senior stakeholders.
Skills
- Representation learning
- Self-supervised/contrastive learning
- Sequence/temporal modeling
- Transformers
- GNNs
- Recommender embeddings
- Python
- PyTorch
- JAX
- SQL
- Distributed data processing
- Cloud-based model training
- ML model productionization
- Customer-360 representations
- Behavioral embeddings
- Recommender systems
- Foundation models
- Privacy in learned representations
- Fairness in learned representations
- Re-identification risk assessment in learned representations
Location
- South San Francisco, CA
Work Type
- Long-Term Contract
Experience Level
- Senior
Benefits
- Medical
- Paid Sick Leave
- 401 (k)
About the Company
- Our client is a world leader in biotechnology and life sciences.
