🛠 Tech Stack

💼 About This Role

You'll architect and lead the development of a state-of-the-art ML inference platform for Roku's advertising ecosystem, handling low-latency, high-throughput serving. Your work will directly optimize performance across hardware, software, and models while mentoring engineers and driving innovation.

🎯 What You'll Do

• Lead design of a SOTA inference platform for ad systems
• Oversee monitoring and observability tooling for ML services
• Resolve performance bottlenecks and system inefficiencies
• Incorporate advances in inference frameworks and hardware acceleration

📋 Requirements

• MS/PhD in CS, ECE, or related field
• 10+ years in large-scale distributed systems, 5+ in leadership
• Strong programming in high-performance languages (C++/Rust)
• Deep expertise in inference frameworks and ML system deployment

✨ Nice to Have

• Experience with GPU acceleration and HPC techniques
• Contributions to open-source ML or systems projects
• Experience leading global, cross-functional teams

🎁 Benefits & Perks

• 🏖️ Paid time off
• 🏥 Healthcare (medical, dental, vision)
• 📈 Equity awards
• 👶 Parental leave
• 💰 401(k)/pension

📨 Hiring Process

Estimated timeline: 3-5 weeks · AI estimate

1. 1Recruiter Screen· 30 min
2. 2Technical Phone Screen· 60 min
3. 3On-site (4-5 rounds)· 4-5 hours