Senior Software Engineer - ML Infrastructure

Latitude AI ( lat.ai ) is building the future of Ford’s autonomy roadmap to make travel safer, less stressful, and more enjoyable for everyone. Bringing this vision to scale, our fully in-house developed hands-free ADAS platform will debut on the all-new Ford Fathom in 2027. 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 redefining the relationship between people and their vehicles for millions of customers. 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 data pipelines, machine learning infrastructure, and evaluation systems that help us understand how autonomy behavior evolves from one software release to the next. Our software turns large-scale driving data into clear, trustworthy insights that help teams across Latitude move forward with confidence. Our work spans the full ML lifecycle, starting with the data. We curate high-quality training and evaluation datasets from real-world and simulated driving, discovering interesting and representative scenarios, labeling them at scale, and organizing them into reusable, well-documented collections. We turn that data into insight, helping engineers understand how the system behaves across a wide variety of driving situations and where the next opportunities lie. We train and ship a range of learned models, from compact classical models to modern deep learning approaches, and build the metrics, experiment tracking, and tools that engineers across autonomy use every day. This role is a great fit for a software engineer who enjoys building reliable, well-tested Python systems and takes pride in producing ML results that people can trust. Day to day, the work is a mix of data and ML infrastructure, model development and evaluation, and internal tools used by partner teams. What You’ll Do: • Curate datasets. Build pipelines that discover, label, and organize driving scenarios from real-world and simulated data into balanced, high-quality training and evaluation sets. • Build data pipelines. Design and maintain scalable, reproducible data pipelines with versioning, provenance, well-designed train/validation/holdout splits, and clear data contracts. • Turn data into insight. Explore dataset composition, coverage, and label quality; characterize how behavior evolves across releases and scenario types; and share findings that help shape model, dataset, and autonomy priorities. • Scale ML infrastructure. Build training, inference, and evaluation pipelines that run smoothly at scale, with robust data loading, checkpointing, and experiment tracking. • Develop and ship models. Train, tune, and productionize learned models, from classical approaches to deep learning, and integrate them into automated analytics pipelines. • Own the metrics. Define, implement, and validate model and release metrics such as precision, recall, F1, ROC AUC, calibration quality, and task-specific metrics, with strong statistical rigor. • Run thoughtful experiments. Set up baselines, ablations, cross-validation, and holdout comparisons; quantify uncertainty; and communicate results that help the team make confident decisions. • Build tools engineers love. Develop dashboards and services that make it easy to compare software versions, explore results at the scenario level, visualize model outputs, and gather feedback from reviewers. • Raise the engineering bar. Design clean