ENGINEERING
Edge AI Systems Engineer
Put models where the latency budget lives: factory floors, retail sites, vehicles and devices. You will build embedded and edge systems that run quantised vision and language models next to the physical process they serve.
- New York
- Engineering
- Full-time
What you’ll do
- Build edge inference pipelines for client deployments in industrial and retail environments
- Quantise and benchmark models against strict latency, memory and power budgets
- Design the sync layer between edge fleets and cloud training/eval loops
- Integrate with sensors, PLCs and existing OT systems safely
- Support pilots on site and harden them into rollouts across hundreds of locations
What we’re looking for
- 3+ years of embedded or edge systems development in C/C++ and Python
- Experience deploying models with ONNX Runtime, TensorRT, LiteRT or llama.cpp on constrained hardware
- Familiarity with edge platforms such as NVIDIA Jetson, Coral or industrial gateways
- Understanding of quantisation and pruning trade-offs for on-device inference
- Knowledge of fleet management and OTA update patterns for deployed models
What we offer
- Competitive salary
- Health, dental, and vision insurance
- Retirement savings plan
- Hardware lab and prototyping budget
- Collaborative work environment