ML Infrastructure Engineer, Ads | Roblox

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.

• 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

• 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

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

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