ML Runtime Engineer

Loft Orbital Solutions
France
Workplace: OnsiteFull timeFunction: Software EngineeringSkills: []

Own the end-to-end compilation and delivery path for ONNX models, turning them into optimized engines for edge accelerators while staying within power and thermal budgets. Build ground-side tooling to benchmark, profile, and validate operator coverage, and ensure mismatched engines are detected and rejected on-node. Contribute to the Space Inference Engine execution providers and SDK for model build and packaging, coordinating closely with the OBSW/Runtime team.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Loft Orbital Solutions
Loft Orbital Solutions
2 months ago

ML Runtime Engineer

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 9 hours agoStatus: Live

Job Summary

Own the end-to-end compilation and delivery path for ONNX models, turning them into optimized engines for edge accelerators while staying within power and thermal budgets. Build ground-side tooling to benchmark, profile, and validate operator coverage, and ensure mismatched engines are detected and rejected on-node. Contribute to the Space Inference Engine execution providers and SDK for model build and packaging, coordinating closely with the OBSW/Runtime team.
Location: France
Workplace: Onsite
Employment Type: Full time
Job Function: Software Engineering

Key Responsibilities

  • •Own model compilation by converting ONNX models into optimized engines for target accelerators within power and thermal budgets
  • •Build the ground-side compile and delivery path, including on-node detection and rejection of mismatched engines
  • •Develop performance tooling such as benchmarking, profiling, operator-coverage matrices, and budget validation
  • •Contribute to the Space Inference Engine execution providers and the SDK for model build and packaging
  • •Coordinate with the OBSW/Runtime team to deliver runtime capabilities
Travel: Low travel

Pay and Benefits

Perks:EquityPaid LeaveHealth InsuranceLife InsuranceMeal AllowanceRelocation

Key Requirements

  • •Strong C++ and Python skills
  • •Experience with model compilation, including TensorRT (or equivalent graph compilers)
  • •Hands-on ONNX Runtime, quantization, and inference performance optimization
  • •Experience deploying models to embedded/edge GPU environments, including NVIDIA Jetson
  • •Experience with benchmarking, profiling/performance tooling, and CI/CD including hardware-in-the-loop
Experience:AI EngineeringEdge GPUModel compilationONNX Runtime
Tech Stack:C++PythonONNXTensorRTHailoAMD ROCmNVIDIA JetsonONNX RuntimeQuantizationInferenceBenchmarkingProfilingCI/CDHardware-in-the-loopMesonYoctoDebianRFIQYocto / minimal Debian

Company Brief

Loft Orbital Solutions
Provides satellite rideshare and mission integration services, offering turnkey spacecraft platforms, payload hosting, and mission operations to accelerate deployment of space-based payloads for commercial and government customers.
Industry: Space Technology
Company Size: Medium (51 to 250 employees)
Growth: Growth Stage Startup
Funding: Series B
Headquarters: Long Beach, United States
Founded: 2017
WebsiteLinkedIn