2 days ago
Base Salary
$166k - $273k/yr
Responsibilities
- Design and operate reliable, low-latency online inference infrastructure for production ML models.
- Develop infrastructure supporting distributed training workflows.
- Integrate ML pipelines with workflow orchestration systems for reliable multi-stage training.
- Optimize model performance through compilation, batching, quantization, GPU utilization, kernel optimization, caching, and runtime tuning.
- Improve monitoring of latency, throughput, errors, cost, saturation, and model health.
- Support model iteration while maintaining production safety, scalability, reliability, and cost efficiency.
- Improve model packaging, artifact validation, compatibility testing, deployment automation, and serving workflow reproducibility.
- Lead cross-team architectural improvements for the online ML platform.
Requirements
- Strong experience building and operating production-grade online ML inference systems and model-serving frameworks.
- Experience with distributed systems, Kubernetes, autoscaling, service reliability, and production observability.
- Strong Python programming skills and experience with production ML systems and high-scale services.
- Experience with PyTorch and modern model deployment workflows, including packaging, validation, and serving lifecycle management.
- Experience designing safe model rollouts, canary testing, A/B experimentation, and automated rollback.
- Strong understanding of latency, throughput, reliability, scalability, and cost tradeoffs in online systems.
- Proven ability to lead technical direction and influence architectural decisions across teams without formal authority.
Benefits
- Comprehensive health, life, and disability insurance, with offerings varying by country and employment status.
- Commute subsidy, employee stock ownership, and competitive retirement or pension plans.
- Generous vacation and personal days.
- New-parent leave and family-care programs.
- Office food and snacks.
- Mental health and wellbeing programs, employee resource groups, and a global employee assistance program.
- Training and development programs.
- Volunteering and donation matching program.
Tech Stack
Categories
About Unity
Unity is a public software company that builds the Unity real-time 3D engine and services for creating, operating, and monetizing games and interactive 3D content across mobile, PC, console, and XR. It sells subscription licenses and usage-based services such as cloud build, ads, and analytics to studios and enterprises in gaming, automotive, film, and AR/VR. Founded in 2004 and headquartered in San Francisco, it trades on the NYSE (U).