Edge Ai Systems Engineer

Summary

Join Janea Systems (USA), a leading software engineering firm, as an Edge AI Systems Engineer. This remote position, open to European residents, requires expertise in AI/ML model development, training, optimization, and deployment on edge devices. You will leverage frameworks like PyTorch and TensorFlow Lite, working with microcontrollers, SoCs, and NPUs. The role demands strong analytical and communication skills, collaboration with various teams, and experience in model compression techniques. Flexible working hours and a competitive compensation package with benefits are offered.

Requirements

• Strong proficiency in PyTorch, TensorFlow Lite (TFML), ONNX and Python
• Familiarity with AI model building blocks, inference flow, edge ML models, and AI model compiler
• Experience with small transformer models (and multimodal models)
• Experience with Microcontrollers, SoC, Arm Ethos-U class of NPUs and Arm Ethos-vela tools
• Experience with ML Frameworks, Model training, optimization & compression for edge ML (for Ethos-U NPU class) devices
• Experience in fine-tuning models for edge-specific deployment on limited resource devices
• Experience with model compression, quantization and pruning
• Excellent communication skills and experience working with various teams

Responsibilities

• Develop and Optimize AI Models: Design, train, and fine-tune AI/ML models for deployment on edge devices, ensuring performance and accuracy on resource-constrained hardware
• Edge-Specific Deployment: Implement and optimize AI solutions on microcontrollers, SoCs, and NPUs (e.g., Arm Ethos-U), leveraging tools like Arm Ethos-vela
• Model Compression and Efficiency: Perform model compression, quantization, pruning, and other optimization techniques to ensure efficient inference at the edge
• Collaborate Across Teams: Work closely with engineering, delivery, and client teams to understand requirements, address challenges, and deliver scalable AI solutions
• Leverage Frameworks and Tools: Utilize ML frameworks such as PyTorch, TensorFlow Lite (TFML), and ONNX for model development and deployment workflows

Preferred Qualifications

• Bachelor's/master's degree in computer science or electrical engineering with 5+
• Proficiency with essential tools: PyTorch, TFML, Arm Ethos-U NPU
• Strong coding and debugging skills
• Proven track record in customer support
• Self-motivated team player with strong interpersonal skills

Benefits

• Competitive compensation with benefits, paid vacation, and sick leave
• The opportunity to work with a globally diverse team of top Engineering talent on the industry’s toughest Engineering challenges
• Ultra-flexible working conditions – we provide a generous office equipment allowance so you can work from home, we can also provide you with a desk at an office/coworking facility near you, or use both. No business travel necessary
• An enjoyable, start-up work environment, with excellent opportunities for professional growth and development
• Flexible working hours – as a remote-first company, our focus has always been on getting the job done well, not when or where it gets done