Senior Embedded ML Engineer — Real-Time Edge AI for Vision

Allen Control Systems; Mountain View (CA); On-site; USD 180,000 - 250,000; Full time

Benefits offered by this job

ACS Equity Package

Health, Dental, Vision Insurance

Paid Time Off

Job summary

Allen Control Systems in Mountain View, CA, is seeking a Senior Embedded Machine Learning Engineer to own end-to-end deployment of trained ML models onto resource-constrained edge hardware. You will optimize models, convert formats with ONNX/TensorRT, and build the C++ infrastructure that hosts inference on devices.

You’ll work closely with CVML, embedded firmware, and product teams to meet strict latency, memory, power, and thermal budgets while ensuring real-time performance in the field.

Qualifications

• At least 10+ years in software or systems Eng; 2+ yrs deploying ML to embedded/edge devices.
• Strong C++ proficiency; CUDA experience; familiarity with edge AI runtimes and inference tooling.
• Experience optimizing models for latency, memory and power on constrained hardware.
• Knowledge of embedded/edge platforms (NVIDIA Jetson, ARM cores) and Linux/RTOS.

Responsibilities

• Deploy ML models to edge hardware with quantization, pruning, distillation, and graph optimization.
• Profile inference on accelerators (GPUs, NPUs, DSPs, FPGAs) to hit latency and power targets.
• Develop C++ code for on-device inference pipelines and memory management.
• Build test harnesses to verify accuracy against references and regressions.
• Collaborate with CV/ML, firmware, and product teams to meet performance targets.

Skills

C++

CUDA

PyTorch

Edge inference

Education

Bachelor’s or Master’s in CS/EE/CE

Tools

TensorRT

ONNX Runtime

TensorFlow Lite

Job description

Allen Control Systems in Mountain View, CA, is seeking a Senior Embedded Machine Learning Engineer to own end-to-end deployment of trained ML models onto resource-constrained edge hardware. You will optimize models, convert formats with ONNX/TensorRT, and build the C++ infrastructure that hosts inference on devices.

You’ll work closely with CVML, embedded firmware, and product teams to meet strict latency, memory, power, and thermal budgets while ensuring real-time performance in the field.