Staff ML Engineer - Recommendation Systems (Remote)

Quora; United States; Remote; USD 240,000 - 320,000; Full time

Job summary

Quora is seeking a Staff Machine Learning Engineer to define the technical future of its recommendation ecosystem. You will own the direction for feed ranking, lead high-impact modeling bets, and pioneer integration of LLMs to redefine understanding and ranking of content.

You will scale recommendation surfaces beyond the home feed, mentor engineers, and drive AI-assisted development to accelerate shipping velocity across the organization.

Qualifications

• 4+ years of professional experience building and optimizing Home Feed recommendation systems for social media and user-generated content platforms.
• Experience leading large-scale ML projects end-to-end with measurable outcomes.
• Deep knowledge of the full recommender stack: candidate generation, retrieval, ranking, re-ranking, embeddings, and multi-objective optimization.
• Publications at venues like RecSys, KDD, NeurIPS, or ICML.

Responsibilities

• Define the technical direction for Quora’s home feed recommendation systems.
• Lead the highest-impact projects across the recommender stack from candidate generation to multi-objective optimization.
• Drive measurable improvements in user engagement and content quality through online experiments.
• Take end-to-end ownership of ML systems, including data pipelines, feature engineering, model training, and production integration.

Skills

Machine learning

Recommender systems

Leadership

Python coding

Education

BS/MS/PhD in Computer Science

Tools

Python

C++

Job description

Quora is seeking a Staff Machine Learning Engineer to define the technical future of its recommendation ecosystem. You will own the direction for feed ranking, lead high-impact modeling bets, and pioneer integration of LLMs to redefine understanding and ranking of content.

You will scale recommendation surfaces beyond the home feed, mentor engineers, and drive AI-assisted development to accelerate shipping velocity across the organization.