Full-Stack AI Engineer (Computer Vision & Back-end Focus)

StellDirVor is an independent consulting, trade and technology company specializing in immersive technologies for healthcare. We support organizations in implementing digital innovations — Virtual, Augmented, and Mixed Reality as well as AI — particularly for learning, training, and real-time assistance in clinical and care environments. By combining technology and healthcare, we help optimize processes, improve knowledge transfer, and enhance quality of care.

Supported by a Germany (ZIM) and Taiwanese (GIPIP) partnership grant, we are currently developing ARAIAS — an AR- and AI-based hands-free training and assistance system for chronic wound care. Using AR smart glasses, the system enables 3D wound capture, AI-supported analysis, and standardized remote expertise and documentation directly at the point of care. ARAIAS introduces a new approach to hands-on, safe, and evidence-based learning and training in clinical settings, with the long-term goal of reducing workload for healthcare professionals and improving care outcomes.

We're at an early and exciting stage — moving from concept to working prototype. The near-term focus is on validating the AI models, establishing the core technical foundations, and building toward a proof of concept we can test in real education and clinical settings. As the project matures, the work will naturally evolve from experimentation and prototyping into more structured development and productionization.

Notes:

Location for this role: Remote (Germany) - due to the nature of the project, we can only consider candidates who are already residing in Germany.

TASKS

• Design and build AI models for wound analysis — from architecture decisions through evaluation and iteration, with a focus on getting to reliable, clinically meaningful outputs
• Apply computer vision techniques — object detection, segmentation, depth estimation, or 3D reconstruction — to real medical imaging challenges
• Handle pre-processing and post-processing of multi-sensor imaging data — including 2D images, depth maps, and other sensor inputs
• Design and build REST APIs and cloud infrastructure that connect and support all system components
• Prototype hardware-software integration — interfacing with smartglass SDKs and sensor APIs to establish data capture pipelines from device to back-end
• Design and build REST APIs, cloud infrastructure, and data pipelines that connect and support all system components
• Integrate AI models into application layers — inference endpoints, model serving, versioning, and performance monitoring
• Make pragmatic architectural decisions appropriate for the current prototyping stage
• Set up CI/CD, containerization, and basic observability to keep the team moving fast
• Support integration points between the back-end / AI layer and the Unity-based front-end (nice to have)

REQUIREMENTS

Must-Have

• Hands-on experience with computer vision — image segmentation, object detection, and classification.
• Experience designing and adapting model architectures — going beyond basic fine-tuning to make informed decisions about model structure, loss functions, and training strategies
• Ability to evaluate model outputs critically — not just metrics, but understanding what the results mean in context
• Back-end engineering proficiency — REST API design with Python as the primary language
• Cloud platform experience (AWS / GCP / Azure)
• Comfort working with hardware SDKs and APIs, and able to independently navigate technical documentation and integration guides to establish device-to-server data flows
• Comfortable with Docker and basic CI/CD pipelines
• Familiarity with ML tooling: PyTorch or TensorFlow
• Fluent in English, German is a bonus
• Given the early stage of the project and the lean team structure, we are looking for someone who can take initiative, own problems end-to-end, and make pragmatic technical decisions independently.

Strong Plus

• Database experience — PostgreSQL, NoSQL, object storage (S3 / GCS)
• Unity experience or familiarity with Unity's integration patterns
• Familiarity with semi-supervised learning — leveraging limited or partially labeled data, relevant when annotated wound imaging data is scarce
• Experience with 3D data pre-processing and post-processing — depth map handling, point cloud cleaning, mesh reconstruction, or similar
• Familiarity with hardware SDK integration — experience interfacing with smart glasses, depth sensors, or similar hardware to extract and stream sensor data
• Exposure to multi-modal learning — combining RGB and depth or LiDAR data into unified model inputs

BENEFITS

• Meaningful work — You help shape how technology redefines education and training in healthcare, with real impact on clinical outcomes
• Ownership and creative freedom — You work autonomously, contribute your ideas directly, and have a genuine say in how the system is built
• A learning culture — We support personal and professional growth through knowledge sharing, access to innovative tools and methods, and a dedicated learning budget
• Flexible working — Remote-friendly setup with the option to work from our Munich office
• Flat hierarchies and team spirit — A small, open, and trust-based team where communication is direct and everyone's voice matters
• International collaboration — Work alongside a Taiwan-based partner covering technology, hardware, and research

Notes:

• Due to the nature of the project, we can only consider candidates who are already residing in Germany.
• We are only able to respond to candidates selected for further consideration. If you have not heard from us within four weeks of applying, please consider your application unsuccessful at this time.