Staff Software Engineer, ML Infrastructure

About the Company

Voxel is building the future of Computer Vision and Machine Learning for operations, risk, and safety. We use computer vision and AI to enable existing security cameras to automatically detect hazards and high-risk activities, keep people safe and drive operational efficiencies.

Responsibilities

• Set the technical direction for ML infrastructure at Voxel
• Architect and build training infrastructure for concurrent experiments using PyTorch and AWS
• Own the train-to-deploy handoff, including model export to optimized formats like TensorRT and ONNX
• Implement experiment tracking and lifecycle stacks such as Weights & Biases or MLflow
• Establish DevOps-for-ML best practices including IaC, CI/CD, and observability
• Mentor engineers on ML infrastructure best practices
• Architect for future needs, including on-device inference

Requirements

• 7+ years of experience building large-scale software systems
• 3+ years focused on ML infrastructure or large-scale data infrastructure
• Proven track record of architectural decision-making and tool selection
• Deep fluency in PyTorch and the modern ML training stack
• Strong proficiency in Python
• Pragmatic approach to architectural decisions and shipping
• Strong communication skills for explaining complex tradeoffs

Preferred Qualifications

• Production experience on AWS (S3, EC2, EKS) for ML workloads
• Experience with model export and inference optimization (TensorRT, ONNX)
• Experience with ML orchestration tools (Ray, Flyte, Metaflow, Prefect)
• Familiarity with GPU performance profiling and optimization
• Background in computer vision model training

Benefits

• Equity through Voxel’s Equity Incentive Plan
• Comprehensive health, dental, and vision insurance
• Competitive paid parental leave
• Unlimited PTO and flexible work arrangements
• Daily meals in-office, team events, and annual company onsite