Senior ML Inference Engineer (AI)

TL;DR

Senior ML Inference Engineer (AI/Platform): Building and operating the ML deployment platform that automates the path from trained models to on-vehicle inference for autonomous vehicles with an accent on automation, reliability, and developer experience. Focus on designing agentic tools to diagnose deployment issues and implementing shift-left validation to surface risks early in the cycle.

Location: Remote within the USA, with a hybrid requirement (report to office 3 times a week) for candidates living within a specific radius of GM hubs (Austin, Mountain View, or Sunnyvale).

Salary: $128,700 – $261,300

Company

hirify.global (GM) is an automotive leader developing autonomous vehicle technology to create a world with zero crashes, emissions, and congestion.

What you will do

• Design and operate the ML deployment platform that automates the transition from trained models (e.g., PyTorch) to on-vehicle inference.
• Partner with model development teams to drive the deployment of high-value models into the autonomous vehicle stack.
• Build agentic and LLM-powered tools to diagnose and automate manual deployment-blocking workflows.
• Develop the developer experience layer, including tooling, dashboards, and observability for ML teams.
• Implement shift-left validation to identify compile, runtime, and latency risks early in the development cycle.
• Integrate optimizations from kernels and compiler teams directly into the deployment workflow.

Requirements

• BS, MS, or PhD in Computer Science or a related technical field.
• 3+ years of industry experience in building or operating production platform or infrastructure systems.
• Strong coding proficiency in Python and experience with ML model deployment and inference integration.
• Experience using coding agents (e.g., Cursor, Claude Code, GitHub Copilot) as part of the engineering workflow.
• Must be based in the US or eligible for relocation to the US.
• Ability to travel up to 25%.

Nice to have

• Experience with orchestration frameworks such as Airflow, Temporal, Flyte, Ray, or Kubeflow.
• Familiarity with the NVIDIA GPU stack (CUDA, TensorRT, Triton, torch.compile, ONNX).
• Experience with inference-serving frameworks like vLLM, TorchServe, or Ray Serve.
• Background in autonomous vehicles, robotics, or safety-critical ML domains.
• Open-source contributions to PyTorch, Ray, Airflow, or related projects.

Culture & Benefits

• Comprehensive health, dental, and vision programs, including HSA and FSA options.
• Retirement savings plan, life insurance, and tuition assistance.
• Paid vacation, holidays, and sickness/accident benefits.
• GM vehicle discounts.
• Hybrid work flexibility for those near company hubs.