Autonomy ML Engineer: Real-Time End-to-End Deployment

Socket.dev; Santa Clara (CA); On-site; USD 170,000 - 240,000; Full time

Job summary

Socket.dev is hiring a high-impact Machine Learning Engineer to build, optimize, and deploy production ML models for their autonomous vehicle stack in Santa Clara, CA. You will collaborate with perception, prediction, planning, and systems teams to ensure models are efficient, scalable, and production-ready for both on-vehicle and cloud workflows.

The role is onsite five days a week in Santa Clara, focusing on end-to-end model development, real-time deployment, and scalable ML infrastructure.

Qualifications

• Strong Python with ML frameworks (PyTorch/TensorFlow).
• Experience deploying ML in production on real-time systems.
• Experience with ML workflows from data to deployment is expected.

Responsibilities

• End-to-end ML lifecycle ownership from data to monitoring.
• Develop and optimize autonomous driving models for perception, prediction, planning.
• Design efficient networks to meet real-time, embedded constraints.
• Integrate models into C++-based autonomy systems and optimize inference.

Skills

Python

PyTorch

TensorFlow

C++

ML deployment

Profiling

Education

MS or PhD in CS/ML/Robotics/EE/Statistics

Tools

CUDA

TensorRT

Job description

Socket.dev is hiring a high-impact Machine Learning Engineer to build, optimize, and deploy production ML models for their autonomous vehicle stack in Santa Clara, CA. You will collaborate with perception, prediction, planning, and systems teams to ensure models are efficient, scalable, and production-ready for both on-vehicle and cloud workflows.

The role is onsite five days a week in Santa Clara, focusing on end-to-end model development, real-time deployment, and scalable ML infrastructure.