Senior Software Engineer - Performance Prediction

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: The Performance Prediction team builds the Machine Learning models, evaluation pipelines, and internal tools that help us understand how autonomy behavior changes across software releases. We work on problems that span behavior classification, ride quality detection, probabilistic trajectory prediction, and release regression analysis. Our systems support both classical and modern ML approaches. That includes compact learned classifiers such as tree-based models for behavior and ride quality detection, as well as deep learning-based probabilistic prediction models for more complex autonomy tasks. We also build the software around those models: dataset definition, feature generation, training and tuning workflows, offline metrics, experiment tracking, and tools that help engineers inspect regressions at the slice and scenario level. This role is a strong fit for someone who enjoys building reliable Python systems and applying rigorous ML evaluation methods in a safety-critical domain. In practice, the work is a mix of ML systems development, model and evaluation work, and internal tooling used by partner teams across autonomy. What you’ll do: Build production software for model training, offline evaluation, and release-comparison workflows Develop and improve learned models for performance prediction, including behavior classifiers and probabilistic prediction models Design training, validation, and holdout strategies that produce trustworthy results Define and track model and release metrics such as precision, recall, F1, ROC AUC, calibration quality, and task-specific forecasting metrics Run experiments, tune models, and analyze results with strong statistical rigor Build internal tools that help engineers compare software versions, inspect model outputs, and investigate regressions Partner with autonomy, simulation, and infrastructure teams to move ideas from prototype to production Raise engineering quality through testing, code review, CI, and maintainable interfaces across data, modeling, and product layers 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) Strong software engineering skills in Python, including experience building modular, maintainable, well-tested systems in a shared codebase Experience developing, training, tuning, or productionizing supervised ML models Strong grounding in statistics and experimental design, including experience designing model training and evaluation tests Experience selecting and interpreting model metrics, thresholds, and tradeoffs for real-world decision-making Experience with ML tooling such as PyTorch, scikit-learn, or similar frameworks Experience working with large datasets using SQL, pandas, and NumPy Strong communication skills and the ability to work effectively across software, ML, and autonomy teams Nice to have: PhD in Computer Science, Machine Learning, Statistics, Robotics, or a closely related field is preferred Equivalent research-heavy industry ... (truncated, view full listing at source)