Senior Software Engineer - ML Performance

Latitude AI ( lat.ai ) develops automated driving technologies, including L3, for Ford vehicles at scale. We’re driven by the opportunity to reimagine what it’s like to drive and make travel safer, less stressful, and more enjoyable for everyone. When you join the Latitude team, you’ll work alongside leading experts across machine learning and robotics, cloud platforms, mapping, sensors and compute systems, test operations, systems and safety engineering – all dedicated to making a real, positive impact on the driving experience for millions of people. As a Ford Motor Company subsidiary, we operate independently to develop automated driving technology at the speed of a technology startup. Latitude is headquartered in Pittsburgh with engineering centers in Dearborn, Mich., and Palo Alto, Calif. Meet the team: In the Performance team, we integrate and optimize software solutions from prototypes to the final product. Our main driver is to make the vehicle react as fast and deterministically as possible to its environment. We are involved in multiple cross-functional projects with stakeholders across the whole company: monitoring performance, optimizing foundation libraries, scheduling accelerators intelligently, and generally squeezing more out of the on-vehicle compute resources. As part of the Intelligent Systems organization, we are particularly interested in converting photons into a view of the world, primarily via computer vision and machine learning. But our scope is not limited to perception, and influences the whole autonomy stack. We take pride in having a direct impact on the product quality and viability. Come help us make the world safer, and driving more pleasant. What you’ll do: Architect, design, and implement software solutions that scale from the lab to the customer, for one of the largest-scale robotics projects in history. Collaborate with various teams to understand, integrate and optimize their algorithms and models. Profile and implement efficiency improvements, from PyTorch to C++, balancing requirements with compute constraints. Develop infrastructure and tools which evaluate & optimize AI performance. Drive projects end-to-end and deliver reliable software through continuous integration, automated testing and code reviews, while in a fast-paced, highly autonomous environment which requires a strong safety culture. What you'll need to succeed : Bachelor's degree in Computer Engineering, Computer Science, Electrical Engineering, Robotics or a related field and 4+ years of relevant experience (or Master's degree and 2+ years of relevant experience, or PhD) Expertise in GPU/DSP architecture and heterogeneous embedded computing. Fluency in Python, PyTorch, ONNX, numpy, pandas. Fluency in modern C++, data structure optimization and parallel programming. Strong understanding of an AI deployment flow on an embedded platform. Industry experience writing production-quality, performance-critical code, and maintaining large codebases. Strong analytical abilities to quickly grasp concepts and design solutions. Strong written and verbal communication skills, to collaborate with stakeholders of various backgrounds. Strong desire to learn and grow, with a curiosity for new domains and technologies, and an R&D mindset. What will make you stand out: Master’s or PhD degree in Robotics, ECE, Computer Science, or a related field. Experience scaling model deployment, profiling or evaluation flows in a production embedded system Experience in optimizing deep learning models through compression, quantization, pruning, kernel fusion, distillation, … to achieve better inference latency, memory footprint and/or model accuracy. Experience writing SIMD code. Knowledge of perception or autonomous vehicle data flow and software stack. What we offer you: Competitive compensation packages High-quality individual and family medical, dental, and vision insurance Health savings account with available employer match Employer-matched 401(k)…