🛠 Tech Stack

💼 About This Role

You'll build and operate the infrastructure that brings ML models into production for Unity's global ad platform, processing billions of requests daily. Your work will ensure high-scale, low-latency serving for ranking, bidding, and targeting systems. This role is at the intersection of ML systems and distributed infrastructure.

🎯 What You'll Do

• Design and maintain real-time ML model serving infrastructure
• Build scalable model serving pipelines owning latency and reliability
• Partner with ML engineers to productionize models and improve iteration speed
• Improve observability, performance, and cost-efficiency of ML serving

📋 Requirements

• Experience building ML infrastructure in production
• Proficiency in Golang or Python
• Hands-on experience with Kubernetes at scale
• Familiarity with model serving frameworks like Ray Serve or Triton

✨ Nice to Have

• Experience with feature stores or feature pipelines
• Background in ad tech or real-time bidding
• Familiarity with infrastructure-as-code such as Terraform

🎁 Benefits & Perks

• 🏖️ Unlimited PTO
• 🏥 Comprehensive health insurance
• 📈 Employee stock ownership
• 👶 Parental leave and family-care programs
• 🧠 Mental health and wellbeing programs

📨 Hiring Process

Estimated timeline: 2-4 weeks · AI estimate

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