Staff Machine Learning Engineer, Ads Foundational Representations

Responsibilities

• Providing technical leadership and mentorship to MLEs in the team: driving designs & their review, establishing best practices in analysis, modeling and engineering, keeping the bar high.
• Working closely with team/org leadership developing technical strategy for content-based embeddings & relevance for Ads.
• Developing new or iterating on existing embedding models for advertising use cases, ranging from aggregation pipelines to two-tower architectures and sequence models.
• Working with local and 3rd-party LLMs/VLMs: extract representations, develop evaluation methodologies, prompt tune and fine-tune large models to build state-of-the-art embeddings.
• Building data processing and inference pipelines for the models we develop.
• Qualitative and quantitative evaluation of the various features we develop, end-to-end experimentation from internal benchmarks to downstream recommender system offline metrics to online experiments.
• Ensuring the reliability, scalability, and performance of the ML systems by writing automated tests, monitoring performance, and implementing best practices for model management.
• Participating in modeling and coding reviews: You will review work by other team members and provide feedback to ensure that it meets the team's standards for quality and performance.
• Collaborating with cross-functional teams to understand business requirements and translate them into technical solutions.

Languages