Principal Applied Machine Learning & Systems Engineer

Lux Tronic builds AI-powered inspection and production monitoring systems to help manufacturers run smarter.

We are seeking a Principal Applied Machine Learning & Systems Engineer to design, deploy, and operate production-grade ML systems in real industrial environments. This role spans edge, on-prem, and cloud ML, where reliability, latency, and uptime matter more than offline benchmarks. At the Principal level, you will define architecture, technical standards, and long-term ML strategy across deployments. This role is deeply hands‑on and requires comfort working under real-world constraints such as sensor noise, environmental variability, and mission‑critical uptime.

Location: Remote (Mountain Time preferred)

Schedule: Flexible hours; ~50–60 hours/week

Travel: Quarterly on-site visits to industrial facilities (factories, plants)

• Design and implement ML models for industrial use cases, including predictive maintenance, anomaly detection, quality inspection, and process optimization.
• Build models resilient to noisy, incomplete, and high‑variance industrial data.
• Develop using modern ML frameworks (PyTorch, Tensor Flow, ONNX) and deploy across:
  • Edge and embedded systems
  • On‑prem industrial servers
  • Cloud and hybrid infrastructure
• Implement fail‑safes, fallback logic, and degradation strategies for mission‑critical systems.

• Deploy ML systems using Docker, Kubernetes, and CI/CD pipelines (Git Hub Actions).
• Build and maintain real‑time and batch inference pipelines with strict reliability and latency requirements.
• Integrate ML services with industrial control systems (PLCs, SCADA, edge controllers).
• Develop secure, low‑latency APIs to enable ML integration in industrial environments.

• Optimize models for performance and efficiency using quantization, pruning, and edge‑optimized inference runtimes.
• Balance accuracy, throughput, and resource constraints across heterogeneous hardware.
• Ensure sub‑second decision‑making where required by industrial processes.

• Monitor deployed models for drift, degradation, and infrastructure issues.
• Build dashboards and alerts using Grafana or similar tools.
• Troubleshoot live production issues involving hardware, networking, data quality, and model behaviour with minimal operational impact.
• Partner with industrial engineers and operations teams to translate factory requirements into ML solutions.
• Participate in quarterly on‑site visits to assess deployment environments and optimise systems in place.

• Own ML systems from design through long‑term operation.
• Anticipate failure modes and proactively mitigate risk.
• Deliver high‑quality outcomes under real‑world constraints and tight timelines.

• Define ML architecture and deployment patterns across multiple industrial sites.
• Establish best practices for model lifecycle management, deployment, and monitoring.
• Lead technical trade‑offs between accuracy, latency, reliability, and cost.
• Review designs and implementations across multiple ML initiatives.
• Mentor senior engineers and raise overall engineering standards.
• Act as technical authority during high‑severity production incidents.
• Other duties as assigned.

• Strong Python expertise for ML and production systems.
• Deep experience with ML frameworks (PyTorch, Tensor Flow, ONNX).
• Proven experience deploying ML in industrial, edge, or embedded environments.
• Experience with Docker, CI/CD pipelines, and Git Hub Actions.
• Proficiency with Ubuntu/Linux and Bash scripting.
• Experience building APIs using AWS services (API Gateway, Lambda, Sage Maker).
• Familiarity with industrial protocols (Modbus, OPC UA) and factory systems (PLCs, SCADA).
• Experience monitoring production systems using Grafana or similar tools.
• Strong real‑time debugging and problem‑solving skills.
• Willingness to travel quarterly and sustain a demanding workload.

• AWS IoT Core / Green grass experience.
• Edge inference optimisation (Tensor
  
  RT, OpenVINO, Jetson).
• Prior experience in manufacturing, robotics, or industrial automation.