Related skills
sql python pandas tensorflow pytorch๐ Description
- Lead pCTR/conversion model R&D; calibrate to reduce biases.
- Design debiasing methods (MNS, IPW, counterfactual risk minimization).
- Contribute to MDMT model architecture with MoE, Transformer, LoRA.
- Drive sequence modeling incl. TIGER retrieval and Semantic ID across ads.
- Collaborate on Foundation Models with autoregressive user behavior.
- Formulate ambiguous problems from first principles with clear eval criteria.
๐ฏ Requirements
- PhD or Master in ML, statistics, CS, IR, or related field.
- 6+ years applying ML to ranking, recommendation, or prediction at scale.
- Deep CTR/conversion modeling; DeepFM, DCN, multi-task learning.
- Strong causal inference, bias mitigation; selection and position bias.
- Python and DL frameworks (PyTorch, TensorFlow, JAX); SQL, Spark, Pandas.
- Turn ambiguous problems into well-scoped ML research with rigorous experiments.
๐ Benefits
- Flexible remote work with Flex First policy.
- Competitive compensation with equity grants.
- New hire equity and annual refresh grants.
- Robust ML infra and MLOps for fast experimentation.
- Opportunities to publish and present findings internally.
- Inclusive culture with regular in-person events.
Meet JobCopilot: Your Personal AI Job Hunter
Automatically Apply to Engineering Jobs. Just set your
preferences and Job Copilot will do the rest โ finding, filtering, and applying while you focus on what matters.
Help us maintain the quality of jobs posted on Empllo!
Is this position not a remote job?
Let us know!