Set the vision and strategy for all aspects of model inference and serving at Netflix, ensuring our platform supports the next generation of ML innovation, including LLMs, GenAI, and real-time personalization.
Lead and develop a cohort of engineering managers and technical leads responsible for core functions, including model routing, inference systems, experimentation, serving frameworks, and the performance and scalability of model serving at Netflix.
Drive cross-team and cross-functional alignment, collaborating with ML researchers, product engineering, infrastructure, and platform partners to maximize business and member impact.
Champion operational excellence and continuous improvement, ensuring reliability, scalability, and cost-effectiveness across all model serving systems.
Define and communicate the pillar’s multi-year vision, technical strategy, and roadmap.
Anticipate future platform and business needs, especially as ML architectures and use cases evolve.
Drive the transition from legacy, domain-based serving to a unified, modular, and domain-agnostic serving platform.
Manage and mentor engineering managers and technical leads; build a strong leadership bench.
Foster a culture of high performance, candor, innovation, and inclusion, aligned with Netflix’s values.
Attract, hire, and retain outstanding talent across the pillar.
Set and uphold technical standards for reliability, scalability, and performance across all teams.
Oversee development of foundational serving infrastructure: real-time/batch inference, frameworks, experimentation, control plane, and tooling.
Ensure robust support for diverse model types (deep learning, LLMs, bandits, etc.), hardware targets (CPU/GPU), and SLAs.
Own operational health and reliability at scale, including observability, SLOs, and incident response.
Build and maintain strong partnerships with ML practitioners, product engineering, infrastructure, and platform teams.
Represent the Model Serving pillar to Netflix senior leadership, clearly communicating the vision, progress, and priorities.
Influence and drive alignment on platform direction, investment, and priorities.

Requirements

Proven success managing multiple managers in high-scale ML infrastructure/platform environments.
10+ years of technical experience, with 5+ years in engineering management roles.
Deep expertise in ML model serving, distributed systems, and high-scale production environments.
Strategic thinking with a track record of delivering complex, cross-team initiatives.
Excellent communication and stakeholder management skills.
Experience driving organizational change and leading through ambiguity.
Experience with modern ML frameworks (e.g., PyTorch, TensorFlow), inference engines (e.g., Triton, vLLM), and experimentation platforms is a strong plus.
MS/PhD in Computer Science, Engineering, or related field, or equivalent experience preferred.

Benefits

Health Plans
Mental Health support
401(k) Retirement Plan with employer match
Stock Option Program
Disability Programs
Health Savings and Flexible Spending Accounts
Family-forming benefits
Life and Serious Injury Benefits
Paid leave of absence programs
Full-time hourly employees accrue 35 days annually for paid time off to be used for vacation, holidays, and sick paid time off.
Full-time salaried employees are immediately entitled to flexible time off.

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills & Tools

ML model servingdistributed systemshigh-scale production environmentsreal-time inferencebatch inferenceexperimentation frameworkscontrol planeobservabilitySLOsincident response

Soft Skills

strategic thinkingcommunicationstakeholder managementorganizational changeleadershipmentoringcross-team collaborationinnovationinclusionperformance management

Certifications

MS in Computer SciencePhD in Computer ScienceEngineering degree