Principal Machine Learning Infrastructure Engineer, Ads & Discovery

What this role involves

This role is for a Principal Machine Learning Infrastructure Engineer on the Ads & Discovery team at Roblox. The engineer will build scalable ML infrastructure for large-scale training and serving, working with models like transformers and LLMs. Responsibilities include co-designing models and systems, optimizing GPU utilization, and leading strategic planning for ML systems.

Skills this posting asks for

• machine learning
• infrastructure
• distributed training
• inference
• fsdp
• vllm
• sglang
• cuda
• gpu kernels
• recommendation
• search
• llm
• transformer architectures
• kv-cache
• pruning
• quantization
• data pipelines
• feature engineering
• model serving

Requirements

• 5 years of experience
• Level: principal

From the employer’s posting

Every day, tens of millions of people come to Roblox to explore, create, play, learn, and connect with friends in 3D immersive digital experiences– all created by our global community of developers and creators.&nbsp; <span…