ML Infrastructure Engineer, Ads | Roblox Jobs San Mateo, CA

The Briefed; San Mateo (CA); On-site; USD 240,000 - 340,000; Full time

Benefits offered by this job

Equity compensation

Benefits for full-time employees

Job summary

Roblox in San Mateo is seeking a Machine Learning Infrastructure Engineer to build scalable, high-performance infrastructure powering ML models across Ads & Discovery. You will design systems for training and serving at scale, spanning transformers, large language models, and content-understanding components.

Collaborating with data scientists, core modelers, and platform teams, you will optimize GPU usage, implement efficient KV-cache strategies, and drive architecture and best practices for

Qualifications

• 5+ years designing and deploying large-scale ML systems in production.
• 3+ years leading ML infrastructure engineers.
• Strong communication and collaborative problem solving.
• BS, MS, or PhD in Computer Science, Engineering, or equivalent experience.

Responsibilities

• Co-design models and systems with modelers, data and AI infra engineers, and product teams.
• Investigate trade-offs end to end from data pipelines to low-latency inference.
• Design efficient KV-cache strategies, pruning, quantization, and GPU utilization.
• Work with FSDP, vLLM, SGLang, CUDA, and distributed frameworks for reliable performance.
• Lead planning and roadmap for production ML systems including training and inference.
• Own architecture and best practices for scalable, reliable ML infra.
• Collaborate with data scientists and platform teams to speed up model development.
• Stay current on ML infra industry trends and state-of-the-art practices.

Skills

Large-scale ML infra

FSDP

vLLM

SGLang

CUDA kernel development

Inference optimization

Education

BS/MS/PhD in CS/Engineering or equivalent

Job description

Roblox’s Ads & Discovery business is growing rapidly, and the company is building large-scale ads machine learning infrastructure to deliver more value to users and advertisers. As a Machine Learning Infrastructure Engineer, you will build scalable, reliable, high-performance infrastructure that powers ML systems across the organization, at the scale of hundreds of billions of engagements. You will co-design models and systems at the intersection of model architecture and ML infrastructure, working with core modelers, data and AI infrastructure engineers, and product teams. Your work will span recommendation, search, and agentic applications, including large transformer architectures, LLMs, generative rankers, and content-understanding systems.

Key Responsibilities

• Co-design models and systems, partnering with core modelers, data and AI infrastructure engineers, and product teams to push the boundaries of large-scale training and serving
• Investigate model, data, and systems trade-offs end to end, from data pipelines and distributed training to low-latency inference and production serving
• Design efficient KV-cache strategies, apply pruning and quantization, optimize GPU utilization and memory efficiency, and develop custom kernels where needed
• Work across ML systems technologies such as FSDP, vLLM, SGLang, CUDA, distributed training frameworks, inference engines, and GPU kernels, staying tool-agnostic and focused on step-function gains in model quality, throughput, latency, reliability, and cost
• Lead strategic planning and roadmap execution for production-ready ML systems, including model training, data pipelines, feature engineering, and model inference
• Own the architecture and set engineering best practices for the scalability, reliability, and cost-effectiveness of ML infrastructure (training, serving, and features)
• Work with data scientists, ML engineers, platform teams, and product stakeholders to design, implement, and operate ML platforms that speed up model development and deployment
• Stay current on industry trends in machine learning and infrastructure to adopt leading-edge technologies and practices

Requirements

• 5+ years of experience designing, building, and deploying large-scale machine learning systems in production
• 3+ years of experience tech leading ML infrastructure engineers
• Strong communication skills and a collaborative approach to problem solving
• BS, MS, or PhD in Computer Science, Engineering, or equivalent experience

Skills

Technical Skills

• Large-scale ML training and serving infrastructure
• FSDP, vLLM, SGLang, and distributed training frameworks
• CUDA and GPU kernel development
• Inference optimization (KV-cache, pruning, quantization)
• Data pipelines and feature engineering
• Transformer and LLM architectures

Soft Skills

• Technical leadership of ML infrastructure engineers
• Cross-functional collaboration
• Strong communication
• Strategic planning and roadmap execution

Benefits

• Equity compensation for all full-time employees
• Benefits for full-time employees, with details on Roblox’s careers page