Lightweight Model & Edge Inference Engineer

WorkSprout is a deep-tech engineering and design partner across twelve practice areas — TinyML & Edge AI, Custom AI Development, AI Automation & Agents, Data Engineering & Collection, IoT Solutions, Hardware Prototyping, Robotics & Automation, 3D Design & Modeling, Software Development, Growth & DevOps, Branding & Creative Design, and Startup & Product Launch. We deliver systems that work in production, not just in demos.

You will specialise in compressing and deploying deep learning models for real-time inference on resource-constrained robotic and embedded hardware. Your optimised models will run on Jetson devices, Raspberry Pis, and custom edge platforms with strict latency and power budgets.

• Apply model quantisation (INT8, FP16) and structured pruning to reduce model footprint
• Export models to ONNX, TensorRT, or TFLite for target hardware deployment
• Benchmark inference latency, throughput, and accuracy trade-offs on real devices
• Collect and validate real-world inference data on deployed robot systems
• Optimise memory layout and power consumption for embedded SBC platforms
• Document compression workflows, benchmarks, and performance reports

• Strong Python with PyTorch and model optimisation libraries
• Hands-on experience with TensorRT, ONNX Runtime, or TFLite
• Understanding of quantisation, knowledge distillation, and pruning techniques
• Experience with NVIDIA Jetson (Nano, Xavier, Orin) or Raspberry Pi hardware
• Proficiency in profiling tools (PyTorch Profiler, Nsight Systems, perf)

• Experience with OpenVINO for Intel edge inference targets
• Knowledge of ARM NEON SIMD or RISC-V vector intrinsics
• Familiarity with Triton Inference Server for serving optimised models

• Work at the frontier of edge AI deployment on real hardware platforms
• Competitive salary benchmarked to international rates
• Access to Jetson, Raspberry Pi, and edge device lab
• Dedicated benchmark and research time each week
• Support for conference attendance and technical publication

* Benefits marked with an asterisk apply to permanent employees only.

If your experience matches the requirements and you are ready to work on production engineering and design challenges, submit your application using the button below. We review every submission personally — no automated screening, no ghosting.