Senior Software Engineer, Agility Robotics

• 5+ years of software engineering experience, with at least 2+ years working on ML infrastructure, data platforms or MLOps systems in production environments
• Experience building and maintaining components of modern ML platforms—such as experiment tracking, model registries, training pipelines, or deployment systems
• Familiarity with orchestration and tracking tools (MLflow, WandB, Airflow, Kubeflow, etc.)
• Proficiency with cloud-native platforms (AWS, GCP, or Azure), containers, and IaC (e.g., CDK, Terraform)
• Hands-on experience with processing or modeling multimodal data(sensor logs, camera streams, behaviour traces etc)
• Comfortable collaborating cross-functionally with research scientists, data engineers, and robotics/autonomy teams to ship infrastructure used by others

Desirable

• Join the team building the machine learning platform to power fleet-scale humanoid robotics. As a senior engineer on the ML Infrastructure and Platform group, you will help architect and build the foundational infrastructure for AI and machine learning operations at Agility
• This includes the platform layer for data collection and processing, training, sim and real evaluation, and model management and observability
• Your work will empower our AI teams across perception, controls, skills, and innovation to build and deploy next-generation robot foundation models and end-to-end policies for humanoid robots by providing tools to develop and operationalize machine learning at scale
• Contribute to the design and implementation of the ML platform for orchestrating the end to end AI flywheel of data processing, training, evaluation, and deployment
• Develop reliable workflows across cloud compute, Kubernetes, and continuous automation
• Build core infrastructure components such as the model registry, feature store and experiment tracking tooling
• Own developer-facing APIs and CLI tools that make ML workflows simple and reproducible
• Implement the CI/CD lifecycle for ML that enable continuous retraining, automated testing, and seamless model delivery to production environments
• Work closely with the Staff ML Infra Engineer and cross-functional stakeholders (AI researchers and robotics engineers) to understand requirements and translate them into scalable solutions/systems
• Partner with data platform engineers to integrate ML orchestration and metadata tracking tools with our existing data lake and pipelines
• Apply MLOps best practices: reproducibility, lineage, rollback, monitoring and governance
• Mentor junior engineers and influence the broader cloud platform organization’s roadmap
• Contribute to internal discussions on platform architecture, reliability, and scalability alongside the broader ML and data platform team
• What We’re Aiming For (MLOps Level 2):
• Version-controlled ML pipelines (data, code, and config)
• Automated and reproducible model training and evaluation
• Continuous integration and delivery for ML workflows
• Centralized experiment tracking and performance visualization
• Standardized model packaging and deployment to production
• Monitoring of models post-deployment