ML Encoder Lead - Contract - Bay Area
Ready to shape how AI understands customers by creating advanced representation-learning models from complex behavioural data?
Proclinical is seeking an ML Encoder Lead to focus on customer representation learning and encoder development. The role involves building a shared learned representation of customers using longitudinal transaction, sales, and interaction data.
Primary Responsibilities:
This representation will support downstream generative AI and analytics products. You will design pretraining objectives, train and evaluate encoders, and provide evidence to determine the success of the approach. This is a hands-on role requiring expertise in model design, evaluation, and production-level coding.
Skills & Requirements:
- Proven experience in training encoders or embedding models, including designing pretraining objectives.
- Expertise in representation learning, sequence modeling, and temporal modeling.
- Strong background in handling large-scale behavioral event data.
- Proficiency in Python, PyTorch or JAX, SQL, and distributed data processing.
- Experience with cloud-based model training at scale.
- Familiarity with rigorous evaluation practices and ability to assess embedding quality.
- Ability to communicate technical findings effectively to diverse stakeholders.
- Preferred: Experience with customer-360 representations, recommender systems, or foundation models over event data.
- Preferred: Knowledge of privacy, fairness, and re-identification risks in learned representations.
- Preferred: Publications, patents, or public work in representation learning.
The ML Encoder Lead's responsibilities will be:
- Design pretraining objectives for customer representation learning.
- Train and evaluate encoders, ensuring rigorous testing and validation.
- Develop models using representation learning techniques such as self-supervised or contrastive pretraining, transformers, and graph neural networks.
- Handle large-scale, sparse, longitudinal event data (e.g., transactions, clickstreams, customer journeys).
- Build inductive representations for entities with limited historical data.
- Conduct thorough evaluations, including time-based splits, leakage detection, cold-start scenarios, and transfer to held-out populations.
- Assess embedding quality for downstream applications, focusing on calibration, stability, drift, and subgroup performance.
- Write production-level Python code using frameworks like PyTorch or JAX, and manage distributed data processing and cloud-based model training.
- Transition models from research to production, including data contracts, training pipelines, versioning, serving, monitoring, and reproducibility.
- Present findings and uncertainties to senior stakeholders and recommend adjustments or cessation of approaches when necessary.
Compensation:
If you are having difficulty in applying or if you have any questions, please contact Terri-Anne Gray at t.gray@proclinical.com
If you are interested in applying to this exciting opportunity, then please click 'Apply' or to speak to one of our specialists please request a call back at the top of this page.
Proclinical is a leading life sciences recruiter focused on finding exceptional people and matching them with the finest positions across the globe. Proclinical is acting as an Employment Agency in relation to this vacancy.
By submitting this application, you confirm that you've read and understood our privacy policy, which informs you how we process and safeguard your data - https://www.proclinical.com/privacy-policy
.png)
.png)
