About the Company
Established in 2017, Infinite Orbits is a NewSpace company, based in Toulouse, pushing the boundaries of in-orbit services with cutting-edge spacecraft driven by its own Rendez-Vous solution, an advanced Autonomous Vision-Based Navigation Solution. IO has two generations of missions
"Orbit Guard" provides Inspection and Space Situational Awareness services in GEO.
"Endurance" is a docking service capable of extending the life of GEO telecom satellites, by taking over AOCS takeover for 5 years.
About the Role
Infinite Orbits is hiring a hands-on Senior Computer Graphics Engineer for its Computer Vision & AI team in Toulouse, to take technical ownership of Satellite Rendezvous Simulator (SRS) and drive its evolution into a mission-grade synthetic data and validation platform.
You will own the architecture, roadmap, and fidelity of our simulation environment. It generates the synthetic data used to train, validate, and qualify computer vision and pose-estimation algorithms for in-orbit rendezvous and docking. You will make the key technical decisions, set engineering standards, and be the go to authority on rendering and sensor simulation.
We are a new-space company. We want rigour where it protects the mission and modern software practice everywhere else: automated pipelines, fast feedback, clear gates.
Job Description
Own the simulator’s architecture and technical roadmap, decide priorities and trade-offs between fidelity, performance, and delivery.
Define and justify simulation fidelity requirements (radiometry, materials, illumination, sensor models) and demonstrate that the simulator meets them through measurable validation against real imagery and lab data.
Design and build scalable synthetic data generation pipelines producing annotated datasets for detection, localisation, and 6D pose estimation.
Generate accurate ground truth (poses, coordinates, orientations, depth, masks, metadata) with traceable, reproducible outputs.
Model camera and sensor physics (noise, optics, exposure, distortion) together with the optical engineering team.
Design configurable scenarios covering nominal operations and edge cases (harsh sun angles, eclipse, specular glints, occlusions).
Quantify the sim-to-real domain gap and lead the work to reduce it.
Set and enforce engineering standards for the simulation codebase: code review, testing, CI/CD, and release practice.
Mentor and technically guide junior engineers and interns working on simulation.
Act as the simulation point of contact for ML, CV, robotics, systems engineering, and external stakeholders (customers, agencies, mission reviews).
Support mission readiness through virtual testing, scenario-based evaluation, and evidence for qualification of perception algorithms.
Requirements
6+ years of professional experience in real-time graphics or simulation, including 3+ years of production C++ development in Unreal Engine.
Deep understanding of the rendering pipeline: physically based rendering, materials, lighting, shaders, and GPU performance profiling.
Custom shader development (HLSL) and rendering pipeline customisation in Unreal.
Proven track record of owning a complex graphics or simulation system end to end, including architectural decisions and long-term maintainability.
Comfortable developing, building, and debugging Unreal Engine on Linux (Ubuntu), including building the engine from source.
Practical experience building synthetic data generation pipelines for computer vision and machine learning.
Solid understanding of computer vision fundamentals, particularly detection, localisation, and pose estimation.
Strong C++ and Python for simulation automation, tooling, and data processing.
Hands-on CI/CD, version control, and automated testing experience, and the ability to set these up for a team.
Experience simulating sensor characteristics, environmental variability, occlusions, and difficult illumination.
Understanding of how dataset quality and diversity affect model performance.
Ability to turn operational requirements into configurable scenarios and test cases, and to defend those choices in technical reviews.
Experience mentoring engineers or leading technical work across a small team.
Strong analytical skills with a focus on accuracy, consistency, and reproducibility.
Fluent English. French is a plus.
Nice to have
6D object pose estimation and 3D computer vision.
Sim-to-real transfer and domain adaptation.
PyTorch or TensorFlow.
Unreal Engine Python scripting, engine source modifications, procedural content generation, or headless/automated rendering at scale.
Camera calibration, intrinsics/extrinsics, depth maps, segmentation masks, and other CV ground-truth outputs.
Radiometric or physically accurate rendering (spectral rendering, BRDF measurement, validated sensor models).
Robotics, autonomous systems, digital twins, or physics-based simulation.
Space or other safety-critical domains (aerospace, automotive, defence).
Optimising large-scale data generation for throughput, distributed rendering, and repeatability.
Preparing perception systems for operational deployment.
Full-time on-site in Toulouse for the first year, while you set up the process and work closely with the team.
What we offer
The opportunity to be part of an international team transforming the space industry.
A creative and innovative work environment where ideas turn into reality.
Competitive salary and benefits.