Senior Machine Learning Engineer

Role Summary

Mindtrace is hiring a Senior Industrial Vision \& Edge Systems Engineer to help expand the hardware and sensing capabilities behind its next generation of industrial inspection products. This person will explore, prototype, validate, and productize new inspection hardware approaches across cameras, sensors, optics, lighting, edge compute, and field\-ready demo systems. The role is especially important as Mindtrace moves beyond standard 2D inspection toward richer sensing, more capable edge deployments, integrator\-ready hardware platforms, and smart\-factory quality intelligence. The ideal candidate is a practical hardware innovator: someone who can spot promising new technologies, build credible prototypes quickly, evaluate them rigorously, and turn the best ideas into repeatable systems that work outside the lab.

What You Will Do

\- Design, prototype, and validate new industrial inspection hardware capabilities across 2D, 3D, advanced sensing, edge compute, and automated capture.

\- Scout and evaluate emerging cameras, sensors, lighting methods, optics, fixtures, embedded systems, and industrial compute platforms that could unlock new inspection use cases.

\- Build proof\-of\-concept rigs that test whether a new sensing or hardware approach can solve a real inspection problem better than existing methods.

\- Benchmark edge hardware, sensor throughput, acquisition reliability, and runtime options for real inspection workloads, including latency, memory use, thermal behaviour, maintainability, and deployment constraints.

\- Support ONNX Runtime, TensorRT, OpenVINO, quantization, and standard edge deployment profiles in collaboration with ML and software engineers.

\- Build and maintain portable innovation demos, including tabletop demo boxes, experimental sensor rigs, industrial camera setups, client\-data capture paths, and field\-ready prototypes.

\- Investigate image quality failure modes such as blur, glare, poor focus, lighting variation, camera shift, calibration drift, and fixture inconsistency.

\- Work with integrators and cross\-functional teams on plant\-floor integration concerns, including PLC signals, trigger timing, robot pose, camera status, and industrial networking. \- Produce clear documentation, setup guidance, test results, and recommendations that can be reused by deployment, sales, client, and product teams.

\- Help decide which new hardware, sensor, edge, and capture approaches deserve deeper product investment, pilot validation, or partner development.

Required Skills and Experience

\- Strong hands\-on experience with industrial vision systems, inspection hardware, sensing platforms, robotics, or factory automation environments.

\- Practical knowledge of industrial cameras, lenses, lighting, working distance, field of view, depth of field, exposure, focus, triggering, calibration, and repeatable image capture.

\- Experience evaluating or deploying edge compute for computer vision workloads

. \- Strong Python fluency for prototyping, testing, automation, data capture, hardware evaluation, sensor integration, and benchmark tooling.

\- Ability to debug physical inspection systems end to end, from image acquisition through model runtime and system behaviour.

\- Familiarity with computer vision tooling such as OpenCV and common image\-processing workflows. Page 1 Senior Industrial Vision \& Edge Systems Engineer

\- Strong experimental discipline: controlled testing, clear metrics, repeatable benchmarks, and evidence\-based recommendations.

\- Ability to turn ambiguous inspection challenges into practical hardware experiments, prototype plans, and clear build\-versus\-buy recommendations.

\- Ability to communicate clearly with ML engineers, software engineers, integrators, client teams, hardware partners, and commercial stakeholders.

Highly Beneficial Skills

\- Experience with advanced sensors such as laser line scanners, structured\-light cameras, stereo/depth cameras, 3D profile sensors, high\-speed cameras, smart cameras, hyperspectral, thermal, X\-ray, acoustic, or related industrial sensing technologies.

\- Experience with ONNX Runtime, TensorRT, OpenVINO, model quantization, model export, or edge inference optimization.

\- C or C\+\+ experience for lower\-level hardware, camera SDK, edge runtime, or performance\-sensitive integration work.

\- PLC, HMI, EtherNet/IP, Profinet, SCADA, robot, or controls integration experience. \- Experience with FANUC, Universal Robots, robot\-mounted vision, EOAT, trigger timing, pose repeatability, or automated inspection cells.

\- Experience in automotive, weld inspection, battery manufacturing, precision assembly, metrology, NDT, or quality inspection.

\- Familiarity with industrial camera ecosystems such as Basler, Cognex, Keyence, LMI, SICK, Teledyne, IDS, Sony industrial cameras, or similar.

\- Experience with hardware evaluation, vendor selection, rapid prototyping, proof\-of\-concept development, or technology scouting.

\- Experience designing demo rigs, test fixtures, portable inspection stations, trade\-show systems, or customer\-facing technical prototypes.

Candidate Profile

The strongest candidates will be practical builders who are excited by new hardware capability as much as by robust deployment. They do not need to be deep ML researchers, but they should understand enough computer vision and model deployment to know how sensing choices, acquisition quality, runtime constraints, and factory conditions affect inspection performance. They should be comfortable moving from a vague opportunity to a credible prototype: identifying the right sensor or edge platform to try, building the first rig, measuring whether it works, and explaining what would be required to turn it into a repeatable product capability. This person should be able to answer questions like:

\- What sensing setup is most likely to solve this inspection problem?

\- Which new sensor, lighting method, edge device, or capture architecture should we test next?

\- Is this failure caused by the model, the image, the lighting, the optics, the fixture, the runtime, or the deployment environment?

\- Which edge hardware profile is credible for this workload?

\- What evidence would convince us that this hardware idea is ready for a pilot?

\- Can this demo or prototype survive being shown repeatedly outside the lab?

Pay: £60,000\.00\-£75,000\.00 per year

Benefits:

• Casual dress


• Company events


• Sick pay


• Transport links


• UK visa sponsorship


• Work from home

This listing is from Indeed. View original listing ↗