Senior Applied AI / ML Engineer (H/F)

ABOUT SPACE CARGO UNLIMITED

At Space Cargo Unlimited, we design, deploy, and operate missions in space to conduct experiments and enable manufacturing in microgravity. By using the unique conditions of space, we enable work in biology, materials science, and industrial processes that is not possible on Earth.

Our goal is to make space a practical place for research and production, building reliable in-orbit platforms and operations based on spaceflight heritage.

To support this, we develop AI and digital-twin tools to improve experiment design, simulate physical processes, and increase mission autonomy, making in-space experiments and industrial processes more efficient and scalable.

YOUR MISSION

As Senior Applied AI/ML Engineer, you will lead the hands-on development of the AI and generative models that sit at the core of our digital twin stack and our mission preparation and operations pipelines. You will take ownership of complex AI workstreams end-to-end — from problem framing and architecture, through prototyping and training, to deployment and integration with flight systems.

You will work shoulder-to-shoulder with physicists, systems engineers, and flight operations teams in a multidisciplinary environment that bridges data science, applied physics, and aerospace engineering. You will set technical direction, raise the bar on engineering quality, and mentor more junior engineers — while still writing production-grade code yourself.

KEY RESPONSABILITIES

• Design, train, fine-tune and deploy ML, deep learning, and generative AI models (PyTorch, TensorFlow, JAX) for vision, time-series, multimodal, and scientific data.

• Architect and ship physics-informed and hybrid AI-simulation systems (PINNs, neural surrogates, neural radiance fields, reduced-order models) that fuse first-principles physics with data-driven models.

• Own significant portions of our digital twin stack for in-orbit systems — from data ingestion and simulation coupling to model serving, monitoring, and continuous improvement.

• Translate state-of-the-art research into robust, production-ready prototypes and internal tools, and judge what to build vs. what to defer.

• Process and analyze experimental, telemetry, and simulation data to improve model accuracy, calibration, and trustworthiness for mission-critical use.

• Collaborate closely with systems engineers and flight operations teams to align AI work with operational, verification, and safety requirements of a complex space system.

• Contribute to technical roadmapping, architectural decisions, and hiring; mentor junior engineers and review their work.

• Represent SCU's AI work externally when relevant — papers, conferences, partner programs, and customer interactions.

WHAT WE OFFER

• A senior, high-impact role at the intersection of AI, science, and space — with real ownership and visibility.

• Hands-on exposure to real missions, flight hardware, and experimental data from orbit.

• A collaborative, ambitious team that takes both science and shipping seriously.

• Bordeaux, France — our European R&D hub — with regular collaboration across European and US partners.

• Competitive compensation, equity opportunities, and clear growth path as Space Cargo Unlimited scales its Space-AI capabilities.

Space Cargo Unlimited is an equal opportunity employer. We welcome applications from candidates of all backgrounds and experiences.

ABOUT YOU

• MSc, engineering degree, or PhD in Applied Mathematics, Computer Science, Physics, Aerospace, or a related field.

• 8+ years of hands-on experience building, training, and deploying AI/ML/DL systems in industrial or applied research settings — not purely managerial or advisory experience.

• Proven track record shipping deep learning systems end-to-end: CNNs, Transformers, RNNs, generative models (GANs, VAEs, diffusion), and modern LLM-based architectures.

• Strong software engineering fundamentals: Python and at least one of C++, Java, or similar; clean code, testing, version control, code review.

• Deep proficiency with PyTorch and/or TensorFlow, plus the scientific Python stack (NumPy, SciPy, Pandas, Matplotlib, scikit-learn).

• Solid grounding in neural networks, optimization, numerical methods, and the math behind modern ML.

• Experience working on, and reasoning about, complex systems — ideally a system of systems with hardware, software, and human-in-the-loop components.

• Comfortable operating in fast-moving, mission-driven, multidisciplinary environments; able to communicate clearly with non-AI specialists.

• Fluent English; French is a plus.

BONUS POINTS

• Hands-on experience with digital twins, multi-physics simulation, or simulation engines (Omniverse, Isaac Sim, Gazebo, Unity, Unreal, Abaqus, or equivalent).

• Systems engineering background: V&V, requirements management (e.g., DOORS), MBSE, Agile delivery in a regulated or safety-critical context.

• Track record in generative AI applied to scientific or engineering problems (NeRFs, diffusion models, foundation models for science, surrogate modeling).

• Aerospace, robotics, or other safety-critical industry experience (e.g., space, aviation, automotive, defense).

• Exposure to GPU-accelerated computing, distributed training, MLOps, Docker and Kubernetes.

• Publications, open-source contributions, awards, or invited talks in AI/ML or applied physics.

• Interest or experience in microgravity research, in-orbit manufacturing, or planetary exploration.

• Experience with embedded AI on resource-constrained systems (e.g., drones, spacecraft, edge devices), including optimization for compute, power, and real-time constraints.