AI Engineer (Perception & Edge AI Systems Engineer) (gn) @ Autonomous Navigation Venture, Belgium

About MAHI

At MAHI we are pioneering the next generation of maritime autonomous navigation technology and growing fast.

MAHI builds maritime autonomy for surface vessels. Our hardware enabled software pairs the MAHI Sense marine grade edge computer with the MAHI Bridge operator tools to deliver camera led situational awareness, remote supervision, and collision avoiding local path planning that works even without connectivity. Founded in 2022 and based in Mechelen, Flanders, MAHI grew out of Project Mahi (started in 2015), the team behind Mahi-2, the first autonomous solar vessel to cross the Atlantic in 2021–2022. Today our systems are integrated on new builds and retrofits from 6 to 60 meters, and have been exercised with partners such as Seasats in the US Navy’s Task Force 59 Digital Horizon program.

How we work

We optimize for doing. We ship, learn, and improve in short loops. Ownership over ego. Practical impact over slide decks. Clear communication, fast decisions, and respect for the craft.

Your role

You’ll build perception capabilities that help vessels understand their surroundings and support safe operation. This role sits at the intersection of AI, estimation, and production software engineering: you’ll turn sensor data into robust runtime outputs and make them reliable on edge hardware in real maritime conditions.

What you will do

• Build and ship production-grade perception services end-to-end: from data/validation to deployable, monitored runtime software.

• Combine learned models with classical methods where it makes systems more reliable (filtering, tracking, association, uncertainty handling).

• Work on multi-sensor pipelines and make them stable under real-world constraints (noise, missing data, imperfect timing, harsh environments).

• Build the production toolchain around perception: logging/replay, regression tests, acceptance metrics, and debugging workflows that shorten field issue turnaround.

• Integrate your work into a modular autonomy stack and collaborate closely with R&D, field engineering, and test teams.

• Improve observability and performance of production services (metrics, profiling, safety monitoring, failure detection).

• Contribute to code reviews, documentation, and engineering standards.

Your profile

• Experience in building production software in autonomy, robotics, perception, computer vision, or adjacent domains.

• Strong programming skills in Go or Rust (the other is a plus; C++ welcome as a strong base).

• Strong applied math fundamentals and estimation intuition:

• filtering and tracking concepts

• coordinate frames/transforms and time synchronization

• uncertainty/Bayesian reasoning (practical, not academic)

• Comfortable with estimation/optimization problems and practical numerical methods.

• Experience shipping a perception pipeline from sensor input to runtime outputs (detections/tracks/embeddings), including integration and evaluation.

• Comfortable debugging and improving real systems: logs, tests, performance bottlenecks, reliability issues.

• Fluent in English with clear, concise communication.

Bonus points

• Edge inference / optimization experience (e.g., TensorRT/ONNX Runtime, quantization, profiling).

• Experience with sensor modalities commonly used in perception (camera, radar, LiDAR/point cloud, AIS, positioning/IMU data, or similar).

• Video pipeline familiarity (RTSP; common codecs such as H264/H265/AV1; basic encoding/decoding concepts).

• TypeScript basics to support UI visualization work.

• Docker, Git, CI/CD (and optionally MLOps tools).

What we offer

• A fun, fast-growing and internationally active company

• Learning opportunities from experienced colleagues

• Competitive salary, fringe benefits, and possibility for stock options

• Real impact: your work runs on real vessels, not just demos