Senior ML Runtime & Motion Planning Engineer (Lunch Included)

PlusAI Inc; Santa Clara (CA); On-site; USD 130,000 - 220,000; Full time

Benefits offered by this job

Catered lunch

Unlimited snacks/beverages

401(k) plan

Job summary

PlusAI is seeking an experienced software engineer to design and optimize the production runtime pipeline for ML-based autonomous vehicle planning. You will integrate ML models into a scalable, safety-critical planning software stack and optimize end-to-end inference on embedded platforms.

The role requires strong C++ skills, experience with TensorRT/CUDA/ONNX Runtime, and a track record of delivering high-performance production systems.

Qualifications

• BS, MS, or PhD in Computer Science, Robotics, Electrical Engineering, or related field.
• 4+ years of experience developing high-performance production software.
• Strong C++ with experience building, optimizing large-scale systems.

Responsibilities

• Design, implement, and optimize the production runtime pipeline for ML-based autonomous vehicle planning.
• Integrate ML models into a scalable planning software stack.
• Optimize end-to-end inference performance through algorithm optimization and efficient execution on embedded platforms.
• Develop high-performance C++ components for feature extraction, inference, and runtime orchestration.
• Design runtime validation, safety guardrails, and fallback mechanisms for feasible and compliant trajectories.

Skills

C++ development

Real-time systems

Debugging & profiling

ML inference deployment

Performance optimization

Distributed systems

CI/CD

Profiling tools

Education

BS/MS/PhD in CS/Robotics/EE

Tools

TensorRT

CUDA

ONNX Runtime

PyTorch

Job description

PlusAI is seeking an experienced software engineer to design and optimize the production runtime pipeline for ML-based autonomous vehicle planning. You will integrate ML models into a scalable, safety-critical planning software stack and optimize end-to-end inference on embedded platforms.

The role requires strong C++ skills, experience with TensorRT/CUDA/ONNX Runtime, and a track record of delivering high-performance production systems.