Senior Software Engineer - ML Infrastructure

Description

The company is building a hands-free driver assistance platform, developed entirely in-house, that will debut on the all-new Ford Fathom in 2027.

The company is a Ford Motor Company subsidiary that develops automated driving technology on a startup pace. It is headquartered in Pittsburgh, with engineering centers in Dearborn, Mich., and Palo Alto, Calif.

You would join the Performance Prediction team, which builds the data pipelines, machine learning infrastructure, and evaluation systems that show how autonomy behavior changes from one software release to the next. The team turns large-scale driving data into insights that other teams rely on.

The team works across the full ML lifecycle, beginning with data. It curates training and evaluation datasets from real-world and simulated driving, finds representative scenarios, labels them at scale, and organizes them into documented, reusable collections. It then trains and ships learned models, ranging from compact classical ones to deep learning, and builds the metrics, experiment tracking, and tools that autonomy engineers use daily.

The role suits a software engineer who likes building reliable, well-tested Python systems and wants ML results that people can trust. Your days will mix data and ML infrastructure, model development and evaluation, and internal tools used by partner teams.

Responsibilities

• Build pipelines that find, label, and organize driving scenarios from real-world and simulated data into balanced, high-quality training and evaluation sets.
• Design and maintain scalable, reproducible data pipelines that support versioning, provenance, careful train, validation, and holdout splits, and clear data contracts.
• Analyze dataset makeup, coverage, and label quality. Describe how behavior changes across releases and scenario types, and share findings that guide model, dataset, and autonomy priorities.
• Build training, inference, and evaluation pipelines that scale well, with robust data loading, checkpointing, and experiment tracking.
• Train, tune, and productionize learned models, from classical methods to deep learning, and plug them into automated analytics pipelines.
• Define, implement, and validate model and release metrics, such as precision, recall, F1, ROC AUC, calibration quality, and task-specific measures, applying sound statistics.
• Set up baselines, ablations, cross-validation, and holdout comparisons. Quantify uncertainty and communicate results so the team can decide with confidence.
• Build dashboards and services that compare software versions, explore results by scenario, visualize model outputs, and collect reviewer feedback.
• Design clean interfaces between data, modeling, and product layers. Champion testing, type checking, code review, and fast, dependable CI.
• Work with autonomy, simulation, data, and infrastructure teams to move ideas from prototype to production.

Requirements

• A bachelor's degree in computer science, computer engineering, electrical engineering, robotics, or a related field and 4+ years of relevant industry experience, or a master's degree and 2+ years of relevant experience.
• Strong Python skills, including designing modular, maintainable, well-tested systems in a shared codebase.
• Experience building end-to-end ML systems, from data pipelines and dataset curation through training, evaluation, and production, with tools such as SQL, pandas, PyTorch, or scikit-learn.
• Experience designing scalable ML infrastructure, such as training and evaluation pipelines, experiment tracking, model serving, or distributed jobs.
• Solid grounding in statistics and experimental design, including choosing evaluation strategies, metrics, and thresholds for real-world decisions.
• Clear communication and the ability to work well across software, ML, and autonomy teams.
• Experience with probabilistic forecasting, sequential, or graph-based models, and with classical methods such as gradient boosting.
• Experience with calibration, uncertainty estimation, ablation studies, error analysis, or comparing results across releases.
• Experience with data-centric ML, such as active learning, auto-labeling, embedding-based search, or dataset versioning.
• Experience with orchestration, experimentation, and internal tools such as Dagster, Airflow, Ray, Weights & Biases, Dash, or Streamlit.
• Experience with Bazel or other large-scale build systems.
• Autonomous driving or robotics experience is helpful but not required.

Conditions

The expected base salary for this full-time role in California is $179,200 to $268,800 USD. Starting pay depends on job-related factors, including exact work location, experience, relevant training and education, and skill level.

Latitude employees may also join the annual bonus programs and equity compensation, subject to eligibility requirements.

You must be legally authorized to work in the United States on a permanent basis. Employment eligibility will be verified at hire. Visa sponsorship is available for this role.

Equal opportunity statement is omitted here, as it is not part of the posting's conditions.

Benefits

• Competitive compensation packages.
• Medical, dental, and vision insurance for individuals and families, plus a health savings account with an available employer match.
• Employer-matched 401(k) with immediate vesting.
• Employer-paid group term life insurance, with the option to buy voluntary life insurance.
• Paid parental leave, an adoption and surrogacy support program, and paid medical leave.
• Unlimited vacation and 15 paid holidays.
• Daily lunches, snacks, and drinks in all offices.
• Pre-tax accounts for healthcare and dependent care, and pre-tax commuter benefits.
• Monthly wellness stipend and backup child and elder care.
• Professional development reimbursement and an employee assistance program.
• Discounts on legal services, identity theft protection, pet insurance, and more.
• Employee resource groups, a quarterly team activity stipend, and wellness initiatives.