Spotify1 день назад
Staff Machine Learning Engineer, Personalization
Зарплата не указана
PermanentNew York
Обязанности
- 01Own and improve the machine learning models and systems that power the Home feed, including the Shortcuts experience
- 02Design, build, and ship personalized recommendations that serve millions of Spotify listeners globally
- 03Build content recommendation systems for emerging agentic and AI-powered user experiences
- 04Train, fine-tune, evaluate, and optimize large language models using techniques such as supervised fine-tuning (SFT), distillation, and parameter-efficient training approaches
- 05Partner closely with product managers, engineers, data scientists, and designers to define and execute experimentation strategies
- 06Drive A/B testing, monitoring, model evaluation, and continuous optimization of recommendation quality, reliability, and cost efficiency
- 07Improve ML platform capabilities, data pipelines, and production systems that support personalization at Spotify scale
- 08Drive technical direction in ambiguous problem spaces and contribute to the long-term architecture of personalization systems
- 09Mentor and support other machine learning engineers, helping raise the bar across the team
Требования
- 01You have 8+ years of experience building and deploying machine learning systems in production environments
- 02You have deep expertise in recommendation systems, ranking models, personalization, or large-scale content discovery platforms
- 03You have strong proficiency in Python and hands-on experience building machine learning systems with PyTorch
- 04You are experienced with large language model training, fine-tuning, evaluation, and optimization techniques including SFT, distillation, and LoRA
- 05You have worked with large-scale inference systems and understand the challenges of latency, reliability, and cost optimization
- 06You care deeply about creating high-quality user experiences through thoughtful application of machine learning
- 07You communicate effectively across technical and non-technical audiences, and you influence technical decisions beyond your immediate team
- 08You know how to design, execute, and interpret online experiments and A/B tests to improve user outcomes
- 09You have experience operating distributed machine learning workloads using technologies such as Ray, FSDP, HSDP, or similar frameworks
- 10You are experienced building and maintaining data pipelines and orchestration workflows using technologies such as Flyte, Airflow, BigQuery, and cloud-based storage platforms
Условия
- 01We offer you the flexibility to work where you work best
- 02For this role, you can be within the North Americas region as long as we have a work location
- 03This team operates within the Eastern Standard time zone for collaboration