Skip to main content
TALENT247 // SPECIALIST AI EXECUTIVE SEARCH & TECHNICAL RECRUITMENT
OPS · MLOps & Platform

Senior Simulation Compute & MLOps Platform Engineer

Toronto, ON, Canada · Full-time · Hybrid

AI Specialism

MLOps & Platform

Workplace

Hybrid

Location

Toronto, ON, Canada

Compensation

CA$160k – CA$215k

annual package

Role Dossier & Specification

REF: SENIOR-SIMULATION-

THE CLIENT & MANDATE

Our client is a physical-AI unicorn headquartered in downtown Toronto developing next-generation autonomous freight technology built from the ground up around a closed-loop generative neural simulator. Rather than logging tens of millions of brute-force highway miles to discover safety-critical edge cases, their platform synthesizes reactive traffic worlds and sensor-accurate scenarios in software to train and stress-test end-to-end driving models continuously.

They are partnering with Talent247 to hire a Senior Simulation Compute & MLOps Platform Engineer in Toronto. Joining their Simulation & ML Infrastructure group, you will own the high-throughput GPU orchestration engine that executes millions of closed-loop virtual miles overnight, ensuring research scientists and autonomy engineers receive deterministic, reproducible safety signals on every model commit.

KEY RESPONSIBILITIES

  • Architect, scale, and operate distributed Kubernetes and Ray GPU compute pipelines executing tens of thousands of concurrent neural sensor-simulation and closed-loop evaluation jobs daily.
  • Design deterministic simulation replay, artifact caching, and frame-level debugging tooling so autonomy engineers can reproduce exact multi-agent highway edge cases in seconds.
  • Optimize GPU cluster scheduling, bin-packing, container cold-start times, and NVMe/object-store streaming throughput across cloud and dedicated accelerator footprints.
  • Build automated release-qualification gates, safety telemetry dashboards, and regression-bisect workflows linking model checkpoints directly to closed-loop driving KPIs.
  • Partner with neural rendering and driving-model researchers to profile CUDA/PyTorch bottlenecks across coupled simulator-and-driver execution graphs.
  • Drive infrastructure reliability, Infrastructure-as-Code discipline, cost-per-simulated-mile telemetry, and on-call automation across the ML platform estate.

TECHNICAL ENVIRONMENT & OFFERING

Their engineering environment combines Python, Rust, C++, PyTorch, Kubernetes, Ray, Argo/Flyte, Prometheus/OpenTelemetry, and multi-cloud GPU clusters. Based hybrid in Toronto, our client offers CA$160,000–CA$215,000 base salary alongside competitive equity, full Canadian medical/dental/vision benefits, and relocation support.

Core Requirements

ESSENTIAL QUALIFICATIONS

  • 5+ years of experience in MLOps, ML platform engineering, distributed compute orchestration, or large-scale simulation infrastructure.
  • Production mastery of Kubernetes at scale, including custom operators/controllers, GPU scheduling, container runtime optimization, and multi-node job orchestration.
  • Strong software engineering proficiency in Python alongside Rust, Go, or C++ for performance-critical control-plane and data-plane services.
  • Proven experience building high-throughput batch/streaming ML evaluation pipelines, artifact registries, and observability stacks (Prometheus, Grafana, OpenTelemetry).
  • Track record diagnosing cross-layer performance bottlenecks across GPU memory, network I/O, object storage, and Linux host configuration.

PREFERRED / BONUS EXPERIENCE

  • Background supporting autonomous vehicles, robotics simulation, game-engine/neural-rendering farms, or HPC Slurm/Ray clusters.
  • Familiarity with PyTorch distributed execution, TensorRT, CUDA profiling tools (Nsight Systems), and CI/CD hardware-in-the-loop or sil-in-the-loop testing.

Position Telemetry

Location Toronto, ON, Canada (Hybrid)
Department MLOps & Platform
Employment type Full-time
Workplace type Hybrid
Salary range
CA$160k – CA$215k annual package