Staff Machine Learning Engineer, Home Surfaces
Staff Machine Learning Engineer building recommendation systems, LLM-powered experiences, and production-scale personalization infrastructure. Requires 8+ years of ML systems experience, deep recommendation expertise, Python/PyTorch proficiency, and distributed ML operations experience.
About the job
Responsibilities
- Own and improve the machine learning models and systems powering the Home feed, including Home Shortcuts.
- Design, build, and ship personalized recommendations for millions of listeners globally.
- Build content recommendation systems for agentic and AI-powered user experiences.
- Train, fine-tune, evaluate, and optimize large language models using supervised fine-tuning, distillation, and parameter-efficient training.
- Partner with product managers, engineers, data scientists, and designers on experimentation strategies.
- Drive A/B testing, monitoring, model evaluation, and continuous optimization of recommendation quality, reliability, and cost efficiency.
- Improve ML platforms, data pipelines, and production systems supporting personalization at scale.
- Drive technical direction in ambiguous problem spaces and contribute to personalization architecture.
- Mentor machine learning engineers.
Requirements
- 8+ years of experience building and deploying production machine learning systems.
- Deep expertise in recommendation systems, ranking models, personalization, or large-scale content discovery.
- Strong Python proficiency and hands-on PyTorch experience.
- Experience with large language model training, fine-tuning, evaluation, and optimization, including SFT, distillation, and LoRA.
- Experience with large-scale inference systems and latency, reliability, and cost optimization.
- Experience designing, executing, and interpreting online experiments and A/B tests.
- Experience operating distributed machine learning workloads with Ray, FSDP, HSDP, or similar frameworks.
- Experience building and maintaining data pipelines and orchestration workflows with technologies such as Flyte, Airflow, BigQuery, and cloud-based storage platforms.
- Strong communication and technical influence across audiences.
Compensation
- Compensation details were not provided.
Skills
Python, PyTorch, Recommendation Systems, Ranking Models, Personalization, LLMs, Lora, Ray, Fsdp, Hsdp, Flyte, Airflow, BigQuery, A/B Testing
Similar jobs
ML Engineering jobs
Scale AI
Denver, COLeads architecture, deployment, and evaluation of reliable agentic ML systems for classified and regulated government environments, including geospatial reasoning, retrieval, memory, and shared infrastructure. Requires 8+ years of production ML experience, Staff-level technical leadership, Python, PyTorch, and an active TS clearance.
Anthropic
San Francisco, CA
Build and operate scalable ML inference infrastructure for Claude’s safety systems, translating safety research into reliable production deployments. The role requires deep production ML infrastructure experience, distributed systems expertise, and proficiency with Python and modern ML frameworks.
Shield AI
San Diego, CA
Develop production C++ perception capabilities for autonomous systems, spanning algorithms, libraries, integration, validation, and release. The role requires deep expertise in at least one perception domain, strong systems debugging, and experience delivering maintainable software in complex robotics or real-time environments.
Garner Health
New York, NY
Leads the reliability, architecture, deployment automation, and monitoring of production machine learning systems. Requires 7+ years of software engineering experience, deep MLOps platform expertise, and strong Kubernetes, cloud, infrastructure-as-code, and observability fundamentals.
Talkiatry
United States
Staff-level engineer responsible for building AI agents and automation, evaluating developer AI tools, and driving adoption across the engineering organization. Requires 8+ years of software engineering experience plus production experience with LLMs, agentic systems, and applied machine learning.