Senior Machine Learning Engineer, Ads Response Prediction

• Own the research and development of pCTR and conversion prediction models, improving accuracy and calibration across advertising surfaces and domains.
• Design and implement techniques to mitigate selection bias, position bias, optimizer’s curse, and other systematic issues in training data, using approaches such as inverse propensity weighting, counterfactual risk minimization, and mixed negative sampling.
• Contribute to multi-domain, multi-task model architectures incorporating mixture-of-experts, transformer-based sequence modeling, and scalable domain adaptation techniques.
• Advance sequence modeling and generative retrieval initiatives, including applications of transformer architectures, learned representations, and semantic identifiers across search, product, and advertising experiences.
• Contribute to broader foundation-model initiatives focused on autoregressive prediction of user behavior and next-interaction recommendations.
• Formulate ambiguous modeling challenges into well-defined research questions with clear hypotheses, evaluation criteria, and experimentation plans.
• Collaborate with data scientists, product managers, and other ML teams while sharing findings through technical reviews, research presentations, paper discussions, and experiment retrospectives.

Requirements

• Master’s or PhD in machine learning, statistics, computer science, information retrieval, or a related quantitative discipline, or equivalent professional experience.
• At least 3 years of combined academic and industry experience applying machine learning to large-scale ranking, recommendation, or prediction problems.
• Strong understanding of click-through-rate and conversion prediction, including architectures such as Deep & Wide, DeepFM, DCN, and multi-task learning approaches.
• Solid knowledge of causal inference, counterfactual reasoning, propensity-based methods, and techniques for addressing training-data bias.
• Proficiency in Python and deep learning frameworks such as PyTorch, TensorFlow, or JAX, along with strong data-manipulation skills using SQL, Spark, and Pandas.
• Demonstrated ability to turn ambiguous problems into well-scoped ML research initiatives and deliver results through rigorous experimentation.
• Strong written and verbal communication skills, with the ability to explain complex modeling concepts to technical and cross-functional stakeholders.
• Experience with advertising ranking, auction-based systems, pCTR, bid optimization, ROAS feedback loops, or marketplace dynamics is a plus.
• Familiarity with autoregressive sequence models, generative retrieval, transformer-based ranking, semantic representations, transfer learning, domain adaptation, or LoRA-based fine-tuning is desirable.
• Research publications in recognized machine learning, information retrieval, recommendation, or related venues are also valued.

Benefits

• Base salary range of $180,000–$190,000 CAD for eligible Canadian-based candidates, with compensation varying according to permanent work location, experience, and skills.
• Eligibility for a new-hire equity grant and annual equity refresh grants.
• Remote-first flexibility, with the source role currently limited to candidates located in Ontario, Alberta, British Columbia, or Nova Scotia.
• Flexible work arrangements designed to support productivity from home, an office, or another suitable location.
• Strong ML infrastructure and MLOps support, including distributed training, automated model deployment, and established data pipelines.
• Opportunities to contribute to cutting-edge machine learning research and collaborate with a broader technical community.
• A learning-oriented environment with opportunities for technical knowledge sharing, research presentations, and professional growth.