Software Engineer, ML Infrastructure

About the Role

As a Software Engineer on the ML Infrastructure team, you will be responsible for developing core systems and infrastructure that perception engineers leverage to field sophisticated, autonomous edge systems.

Key Responsibilities

• Develop core data management systems for perception and autonomy use-cases, including indexing multi-modal sensor data.
• Develop model training/orchestration systems that run across cloud-based and on-premise compute.
• Develop the internal perception platform which enables dataset querying and discovery, orchestrates internal frontier models to tag and curate data, and trains & evaluates models for deployment to edge devices.
• Own core training libraries/SDKs for perception engineers.
• Partner with perception engineers to integrate novel model architectures into standard infrastructure.
• Build and operate core model training & dataset management infrastructure.
• Improve perception engineer-facing tooling & SDKs.
• Integrate frontier models for data augmentation, curation, and synthetic data generation.
• Enable observability & traceability of the full ML lifecycle, including real-time monitoring of training jobs, model evaluation reports, and model registry.
• Build systems that integrate with Fleet Management systems to deliver model improvements to edge systems.
• Partner with business line engineering teams to understand specific data requirements and deliver iterative solutions.

Requirements & Tech Stack

• Strong proficiency in modern Python.
• Exposure to Rust/the Rust ↔ Python toolchain (e.g., PyO3, Maturin).
• Experience with modern deep learning frameworks such as Tensorflow or PyTorch.
• Experience with distributed training paradigms.
• Experience leveraging modern MLOps tooling on the orchestration side (e.g., Modal, Flyte, Airflow, Dagster).
• Experience with common ML observability platforms (e.g., Weights & Biases, MLFlow).
• Familiarity with building and deploying backend services into a Kubernetes environment.

Qualifications

• U.S. Person status is required.
• Eligibility to obtain/maintain a U.S. Top Secret clearance is desirable.