Member of Technical Staff Applied ML RecSys

Role overview

You will be the technical owner for enterprise recommendation system engagements, applying frontier sequential recommendation architectures to real customer problems at scale. The role involves end-to-end applied ML ownership: adapting Liquid Foundation Models for personalization and ranking use cases while meeting production constraints.

Responsibilities

• Own customer recommendation/ranking engagements end-to-end, from requirements through delivery and evaluation
• Translate customer requirements into concrete recommendation model specifications
• Design and execute data pipelines for user interaction data, feature engineering, and training data curation at scale
• Fine-tune and adapt large-scale sequential recommendation models (e.g., HSTU-style architectures) for customer-specific needs
• Create task-specific evaluation plans (ranking quality, latency, throughput) and interpret results
• Build reusable applied tooling and workflows to accelerate future customer engagements

Requirements

• Hands-on experience building or fine-tuning recommendation models at scale (not just off-the-shelf collaborative filtering)
• Experience with sequential recommendation architectures, user behavior modeling, or large-scale ranking systems
• Strong intuition for recommendation data quality and evaluation design, including offline metrics and A/B testing/business metric alignment
• Experience with large-scale data pipelines for user interaction data and feature engineering
• Proficiency in Python and PyTorch, with strong autonomous coding and debugging ability

Nice to have

• Experience with transformer-based recommendation architectures (e.g., HSTU, SASRec, BERT4Rec)
• Experience delivering recommendation systems to external customers with measurable business outcomes
• Familiarity with serving recommendation models under latency and throughput constraints

What success looks like (Year One)

• Independently delivers enterprise recommendation engagements with minimal oversight
• Trusted as the technical owner for tradeoffs between model quality, latency, and business impact
• Builds reusable workflows/tooling that speed up future customer engagements