Software Engineer (SE / Sr SE), Applied ML & Data Mining

Job description

Job responsibilities

• Develop and evaluate mining, retrieval, and ranking methods using signals such as model confidence, disagreement, embeddings, anomalies, temporal behavior, and learned representations
• Build and evolve semantic image/video/scenario search, including text-to-image/video and image-to-image or video-to-video retrieval, vector search, metadata and temporal or spatial filters, task-specific ranking, and…
• Build and operate distributed mining, inference, and indexing pipelines over fleet-scale imagery, video, time-series, and autonomy-system data, including GPU batch inference, embedding generation, reproducible…
• Design and ship mining products end to end: Python APIs and services, relational data models, asynchronous jobs, modern TypeScript/React search and review experiences, deployment, access control, testing,…
• Ensure that your work is performed in accordance with the company’s Quality Management System (QMS) requirements and contribute to continuous improvement efforts

Job requirements

• BS, MS, or PhD in Computer Science, Machine Learning, or a related technical field, or equivalent practical experience
• Hands-on experience developing and evaluating machine-learning, data-mining, computer-vision, or information-retrieval methods with a framework such as PyTorch or TensorFlow, including experimentation, error analysis,…
• Foundations for data-centric machine learning: an understanding of model uncertainty and evaluation, embeddings and similarity search, and how training-data composition shapes model behavior
• Self-driven with a strong sense of ownership: a quick learner who is eager to take responsibility and drive projects forward end to end
• Production full-stack experience spanning backend services and REST APIs, relational data modeling and SQL, and modern JavaScript or TypeScript frontend development using React or a comparable framework
• Experience improving models through data — training or fine-tuning, active learning and data flywheels, hard-example mining, uncertainty or disagreement signals, dataset curation — ideally in autonomous driving,…
• Experience with embedding and multimodal models (CLIP-style models, VLMs), vector databases (Milvus, FAISS, pgvector), or GPU batch inference at scale