> Markdown version of [/jobs/ext/2726644-ml-runtime-engineer](https://www.wearedevelopers.com/jobs/ext/2726644-ml-runtime-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# ML Runtime Engineer

- **Company:** Loft's Ai For Space Group
- **Location:** Toulouse, France
- **Contract:** Permanent contract
- **Skills:** C++ (Programming Language), Continuous Integration, Debian Linux, Image Management, Python (Programming Language), Yocto, ONNX (Open Neural Network Exchange) Format, TensorRT
- **Published:** September 5, 2026
- **Apply:** https://startup.jobs/ml-runtime-engineer-loft-orbital-solutions-8664350

## About the Role

* Strong C++ and Python
 * Model compilation: TensorRT (and/or equivalent graph compilers)
 * ONNX Runtime, quantization & inference perf optimization
 * Embedded / edge GPU deployment (NVIDIA Jetson)
 * Benchmarking & profiling / perf tooling
 * CI/CD incl. hardware-in-the-loop

Nice to Haves:

 * Hailo SDK and/or AMD ROCm compilation (iX10)
 * Writing custom kernels / operator plugins
 * Remote sensing / large-image handling
 * RF / IQ signal data exposure
 * Meson build, Yocto / minimal Debian images
 * Model-weight protection / secure execution

## Description

* Own model compilation: turn partner ONNX models into optimized engines per accelerator (TensorRT, Hailo, AMD/ROCm), within power & thermal budgets
 * Build the ground-side compile & delivery path; define how a mismatched engine is detected/rejected on-node
 * Build performance tooling: benchmarking, profiling, operator-coverage matrices, and budget validation
 * Contribute to Space Inference Engine (execution providers) and the SDK (model build & packaging); coordinate the OBSW / Runtime team


## Related Videos

- [Efficient deployment and inference of GPU-accelerated LLMs​](https://www.wearedevelopers.com/videos/929-efficient-deployment-and-inference-of-gpu-accelerated-llms)
- [Tour de Force: Open-Source LLM Inference Optimization from Simple to Sophisticated](https://www.wearedevelopers.com/videos/100099-tour-de-force-open-source-llm-inference-optimization-from-simple-to-sophisticated)
- [Discover the open source trio you didn’t expect: .NET and PostgreSQL on Linux](https://www.wearedevelopers.com/videos/2042-discover-the-open-source-trio-you-didn-t-expect-net-and-postgresql-on-linux)
- [Trends, Challenges and Best Practices for AI at the Edge](https://www.wearedevelopers.com/videos/630-trends-challenges-and-best-practices-for-ai-at-the-edge)
- [LLMOps-driven fine-tuning, evaluation, and inference with NVIDIA NIM & NeMo Microservices](https://www.wearedevelopers.com/videos/1582-llmops-driven-fine-tuning-evaluation-and-inference-with-nvidia-nim-nemo-microservices)
- [From Perception to Autonomy: Building Agentic Edge AI Robots with ROS 2](https://www.wearedevelopers.com/videos/100295-from-perception-to-autonomy-building-agentic-edge-ai-robots-with-ros-2)

## Related Articles

- [MLops – Deploying, Maintaining And Evolving Machine Learning Models in Production](https://www.wearedevelopers.com/magazine/115-mlops-deploying-maintaining-and-evolving-machine-learning-models-in-production)
- [How We Built a Worry-Free System That Runs for 10+ Years – And What We’d Do Again](https://www.wearedevelopers.com/magazine/751-how-we-built-a-worry-free-system-that-runs-for-10-years-and-what-we-d-do-again)
- [MLOps – What’s the deal behind it?](https://www.wearedevelopers.com/magazine/125-mlops-what-s-the-deal-behind-it)
- [Dev Digest 120 - Apple and peers](https://www.wearedevelopers.com/magazine/455-dev-digest-120-apple-and-peers)
- [Dev Digest 138 - Are you secure about this?](https://www.wearedevelopers.com/magazine/486-dev-digest-138-are-you-secure-about-this)
- [Everything a Developer Needs to Know About MCP with Neo4j](https://www.wearedevelopers.com/magazine/604-everything-a-developer-needs-to-know-about-mcp-with-neo4j)