AI Computer Vision Engineer

Nasze wymagania:
Bachelor's or Master's degree in Computer Science, Robotics, Electrical Engineering, or a related field.
3+ years of hands-on experience with computer vision and deep learning (CNNs, vision transformers, detection/segmentation/tracking architectures).
Strong experience with PyTorch (or TensorFlow/JAX) and the OpenCV ecosystem.
Solid understanding of camera fundamentals: optics, exposure, ISP, lens distortion, calibration, and multi-camera or multi-sensor geometry.
Strong C++ skills and experience integrating ML models into production software.
Experience with CUDA and optimizing inference for embedded or edge platforms (TensorRT, ONNX, quantization).
Experience building data pipelines from collection through labeling, versioning, and evaluation.
Practical experience with real camera hardware, not only public datasets.

Mile widziane:
• Multi-object tracking, sensor fusion (camera + radar/lidar/AIS), or visual SLAM/odometry.
• Thermal/IR or low-light imaging experience.
• Video streaming and encoding (GStreamer, RTSP/SRT/WebRTC) and low-latency pipelines.
• Experience with ROS, MOOS-IvP, Gazebo, or other robotics and simulation tools.
• Synthetic data generation or domain adaptation techniques.
• Understanding of maritime operations, navigation, or COLREGs.
• Background in real-time or safety-critical systems.
Soft skills
• Curious and experimental mindset with fast iteration ability.
• Strong teamwork in cross-functional environments.
• Clear communication across technical and non-technical groups.
• Genuine interest in applied AI and robotics.

O projekcie:
Why join us?
Because what we build actually goes into the water and does the job - for both commercial and military use. It's real-world autonomy, not just theory. We’re a driven and focused team. You’ll have space to try things, ask questions, suggest better ways, and be heard. Your work will actually help shape the product.
If you want to work on something that matters, with people who actually care, this might be your place.
We aim for full transparency and predictable steps in recruitment process:
* Intro interview (30 min)
* Technical interview with polish team
* Technical talk with Boston team
* Final interview with an offer or feedback
If all that resonates with you feel free to send us your resume. We’d love to chat and see if this is a great fit for you. Also, if you believe you have the skills and potential but don't tick every box - we still encourage you to apply. Let's talk and get to know each other.

Zakres obowiązków:
Design, train, and deploy deep learning models for detection, classification, and tracking of vessels, buoys, debris, and other maritime objects using RGB and IR vision systems.
Select, specify, and integrate camera hardware: sensors, lenses, field of view and resolution trade-offs, interfaces, housings, and mounting.
Own camera calibration (intrinsic and extrinsic), time synchronization, and alignment with other sensors such as radar, AIS, and GNSS/IMU.
Build robust perception for harsh marine conditions: glare, spray, fog, low light, horizon motion, and vessel pitch and roll.
Build data pipelines for collection, curation, labeling, versioning, and evaluation, using real-world mission logs and field recordings.
Optimize and deploy models on edge and onboard compute (e.g., NVIDIA Jetson) with TensorRT, quantization, and real-time latency budgets.
Evaluate performance with simulation, replayed logs, and field testing, and define metrics that reflect safety-relevant behavior.
Support field trials and troubleshoot camera and perception issues on real vessels.

Oferujemy:
Opportunity to expand AI capabilities to include Large Language Models (LLMs).
A disciplined engineering environment with room for experimentation and learning.
Flexible hours with 3 required office days in Gdańsk.
Private healthcare.
Sports & wellness allowance.
Eyewear subsidy.
Office stocked with snacks & refreshments.
Team lunch every Wednesday.