Senior Machine Learning Engineer - Model Optimization & Deployment (ADAS/Autonomous Driving)
Job Overview
The Role
We are seeking a Senior Machine Learning Engineer (or strong ML Engineer) to drive the integration and deployment of advanced perception models into Lucid’s production ADAS and autonomous driving systems. This role focuses on model optimization and compression, productizing ML models, ensuring robust performance on automotive-grade hardware, and building scalable pipelines for deployment and validation. You will collaborate with ML researchers, perception engineers, and hardware teams to deliver high-performance, safety-compliant solutions.
Key Responsibilities
- Model Integration & Productization
- Deploy and integrate perception models into Lucid's centralized software stack.
- Transition experimental components into production-ready modules with robust scheduling and diagnostics.
- Model Optimization & Compression
- Optimize inference pipelines using CUDA, TensorRT, mixed-precision, quantization (PTQ/QAT), and model pruning/distillation techniques for real-time performance.
- Profile latency, memory, and compute bottlenecks; improve model and system efficiency on automotive hardware.
- Pipeline Development & Automation
- Build CI/CD pipelines for nightly deployments, HIL verification, and KPI reporting.
- Automate data recording, evaluation frameworks, and regression testing for optimized models.
- Cross-Functional Collaboration
- Work closely with ML researchers, software engineers, and hardware/platform teams to ensure seamless integration.
- Support SDK/tooling development and internal or customer-facing deliverables.
- System Diagnostics & Monitoring
- Implement runtime performance metrics, logging, and error reporting for perception stack reliability.
Required Qualifications
- BS/MS in Computer Science, Electrical Engineering, or related field.
- For Senior ML Engineer: 5+ years (or ML Engineer: 2+ years) of experience in ML/software engineering for perception or autonomous systems.
- Strong proficiency in C++ and Python, with experience in ROS1/2, OpenCV, and GPU acceleration.
- Hands-on experience with ML frameworks (PyTorch) and inference optimization (TensorRT, CUDA).
- Practical experience with at least one compression technique such as quantization, pruning, or distillation.
- Experience with containerization (Docker), CI/CD, and automated deployment pipelines.
- Strong collaboration skills and ability to execute across research and production teams.
Preferred Qualifications
- Experience with automotive perception systems and ADAS software stacks.
- Familiarity with automotive safety standards (ISO 26262, ASPICE).
- Experience deploying INT8/FP16 models and validating accuracy-latency tradeoffs.
- Knowledge of multithreaded scheduling and real-time performance tuning.
- Background in SDK/tooling development and automotive customer integration.
Additional Compensation and Benefits: Lucid offers a wide range of competitive benefits, including medical, dental, vision, life insurance, disability insurance, vacation, and 401k. The successful candidate may also be eligible to participate in Lucid’s equity program and/or a discretionary annual incentive program, subject to the rules governing such programs. (Cash or equity incentive awards, if any, will depend on various factors, including, without limitation, individual and company performance.)
By Submitting your application, you understand and agree that your personal data will be processed in accordance with our Candidate Privacy Notice. If you are a California resident, please refer to our California Candidate Privacy Notice.