Machine Learning Software Developer, In-Vehicle Infotainment

Ford of Canada's operations include a national headquarters, three vehicle assembly and engine manufacturing plants, three parts distribution centres, and three Connectivity and Innovation centres. Ford employs approximately 7,000 people in Canada, while an additional 18,000 people are employees in the more than 400 Ford and Ford-Lincoln dealerships across the country. For more information, please visit www.careers.form.com Ford’s Electric Vehicles, Digital and Design (EVDD) team is charged with delivering the company’s vision of a fully electric transportation future. EVDD is customer-obsessed, entrepreneurial, and data-driven and is dedicated to delivering industry-leading customer experience for electric vehicle buyers and owners. You’ll join an agile team of doers pioneering our EV future by working collaboratively, staying focused on only what matters, and delivering excellence day in and day out. Join us to make positive change by helping build a better world where every person is free to move and pursue their dreams. Join the IVI Intelligence Lab and help build AI features that ship in Ford vehicles. You will work across the stack, from cloud training and serving to on-device inference, in computer vision, speech, personalization, and language models. The IVI Intelligence Lab is a new, small team inside the In-Vehicle Infotainment (IVI) platform organization, built to take AI from experimentation to shipping vehicle features. You will design, train, and deploy AI across the full stack: large-scale training and serving in the cloud, and hard real-time inference on the vehicle's compute platform, powering a new generation of proactive in-vehicle experiences. The work spans computer vision, speech and audio, personalization and prediction, and language models, applying each where it genuinely improves the customer experience. What you'll do... The primary responsibilities for this position include, but are not limited to: Ship on-device AI: Deploy and optimize models on the vehicle SoC using quantization, pruning, and distillation, meeting strict latency, memory, power, and thermal budgets across CPU, GPU, and NPU acceleration. Integrate with the platform: Embed inference in the Android Automotive OS software stack through system services and native (C++ and JNI) code, working against camera, audio, and vehicle signal interfaces. Integrate the same features with cloud services and vehicle APIs where the use case calls for it. Build the data flywheel: Construct cloud training pipelines and MLOps practices that turn vehicle data, under strict privacy controls, into continuously improving models: ingestion, curation, training, evaluation, registries, and drift monitoring. Personalize the vehicle: Develop vision and speech models that recognize who is in the car, so the vehicle can prepare their profile, settings, and preferred one-tap actions, as convenience features on a secure-by-design data path with automatic fallback to the device credential (PIN, pattern, or password). Predict and adapt: Build context engines and predictive models that learn driver behaviour, curate useful next actions before they are requested, and adapt interface surfaces and drive coaching to what perception detects inside and around the vehicle. Advance vehicle perception: Train and evaluate camera-based models for in-cabin and external views, collaborating with ADAS and camera architecture teams on shared camera paths and sensor constraints. Apply GenAI deliberately: Bring small language and vision-language models on device, with function calling behind safety guardrails, distillation from foundation models, and measurable evaluation, choosing open or in-house components where each is strongest. Build LLM applications and agents: Compose LLM-backed features with tool and function calling into IVI and cloud APIs, retrieval, guardrails, and evaluation, choosing on-device or cloud execution per use case. Investigate and evaluate: Research emerging AI/ML technologies, deliver proof of concepts that settle architecture decisions early, and find the right balance between in-house, supplier, and open-source components. Own the lifecycle: Contribute across the entire software lifecycle, from requirements and design through coding, testing, defect resolution, and production monitoring of model health and data drift. Make trade-offs measurable: Publish internal benchmarks and evaluation harnesses so model, platform, and product decisions are grounded in evidence. You'll have... Education: • Bachelor's degree in Computer Science, Software Engineering, Electrical Engineering, or a related field of study Experience: • 4+ years of professional software engineering experience, including production AI/ML development from model development through deployment and monitoring. • Hands-on depth in model optimization (quantization, pruning, distillation) and deployment on embedded or mobile NPUs, using frameworks such as TensorFlow Lite, ONNX Runtime, or SoC vendor SDKs. • Strong Python and C++, Git, and disciplined testing and benchmarking habits. • Experience with training pipelines and MLOps, including data versioning, CI/CD for ML, model registries, and drift monitoring. • Ability to translate ambiguous technical and product questions into hypotheses, experiments, prototypes, and clear recommendations. Even better, you may have... Education: • Specialization in machine learning, such as a master's, graduate certificate, or equivalent coursework. Experience: • Computer vision, speech and audio, or multimodal machine learning for sensor-driven vehicle and in-cabin experiences, including driver or occupant monitoring, face or voice biometrics, and wake-word speech models. • Fine-tuning (LoRA, QLoRA, or preference alignment methods), knowledge distillation, and evaluation of LLM and VLM systems; retrieval-augmented generation in constrained domains. • Hands-on depth in quantization-aware training, model c