Staff Machine Learning Engineer, Personalization

This is a fully remote position, open to applicants in New York.

📋 Description

• Take ownership of and enhance the machine learning models and systems that drive the Home feed.

• Design, develop, and deploy personalized recommendations that cater to millions of Spotify listeners worldwide.

• Create content recommendation systems for new AI-driven user experiences.

• Train, fine-tune, assess, and optimize large language models utilizing various methodologies.

• Collaborate with product managers, engineers, data scientists, and designers to implement experimentation strategies.

• Lead A/B testing, monitoring, model assessment, and ongoing enhancement of recommendation quality, dependability, and cost-effectiveness.

• Enhance ML platform capabilities, data pipelines, and production systems that facilitate personalization.

• Steer technical direction in uncertain problem areas and contribute to the long-term architecture of personalization systems.

• Mentor and guide fellow machine learning engineers, elevating the team's overall performance.

⛳️ Requirements

• Over 8 years of experience in building and deploying machine learning systems in production settings.

• In-depth knowledge of recommendation systems, ranking models, personalization, or large-scale content discovery platforms.

• Strong skills in Python and practical experience in developing machine learning systems with PyTorch.

• Experienced in training, fine-tuning, evaluating, and optimizing large language models.

• Familiar with large-scale inference systems and aware of the challenges related to latency, reliability, and cost optimization.

• Passionate about delivering high-quality user experiences through the thoughtful application of machine learning.

• Capable of effectively communicating with both technical and non-technical audiences, influencing technical decisions beyond the immediate team.

• Knowledgeable in designing, executing, and interpreting online experiments and A/B tests to enhance user outcomes.

• Experienced in managing distributed machine learning workloads using technologies like Ray, FSDP, HSDP, or similar frameworks.

• Proficient in building and maintaining data pipelines and orchestration workflows using tools such as Flyte, Airflow, BigQuery, and cloud-based storage solutions.

🏝️ Benefits

• Spotify is an equal opportunity employer. You are welcomed at Spotify for who you are.

• Committed to inclusivity and ensuring that our entire recruitment process is accessible.

• Reasonable accommodations will be provided during the interview process to assist with your needs.