Senior Software Engineer, ML Ops & Infrastructure

Role

As a software engineer focused on MLOps and deep learning infrastructure, you will design and build the foundational systems that empower robots with advanced machine learning capabilities. You will work within a cross-functional team of engineers and researchers to develop infrastructure that streamlines the training, evaluation, and deployment of large-scale AI models. Your efforts will provide accessible tools for injecting machine learning techniques into the Intrinsic stack, managing compute resources across cloud and on-premise environments, and ensuring that complex model lifecycles are efficient, reliable, and scalable for real-world industrial applications.

How your work moves the mission forward

• Design and implement scalable infrastructure for training and deploying deep learning models on top of a real-time robotic control stack.
• Help optimize data loading and training speed across 1000+ GPU training jobs
• Build data pipelines that support distributed computing to process large volumes of robotics data for model training.
• Develop APIs and tools that allow internal and external researchers to easily integrate machine learning techniques into their workflows. This could involve leading efforts  to open source models and engage with the community.
• Optimize the allocation of compute resources, such as GPUs and TPUs, to reduce cost and latency during model development and create orchestration workflows to successfully run jobs on GKE.
• Create tools for model understanding and analysis to ensure reliability and traceability across the machine learning lifecycle.

Skills you will need to be successful

• Bachelor's degree in Computer Science, Robotics, Machine Learning, or a related technical field.
• 2 years of experience in software development with a focus on MLOps or machine learning infrastructure.
• Proficiency in programming with Python and C++.
• Experience with containerization and orchestration technologies, specifically Docker and Kubernetes.
• Experience with deep learning frameworks such as TensorFlow, JAX, or PyTorch.
• Experience with cloud computing platforms like Google Cloud Platform.
• Basic Front-end experience

Skills that will differentiate your candidacy

• Master’s degree or PhD in Computer Science, Robotics, or a related field.
• Comprehensive knowledge of the entire image processing workflow, from initial sensor data acquisition (drivers, OS) up to the final application logic and decision-making.
• Experience with MLOps toolkits such as Kubeflow.
• Hands on experience with CUDA optimization or deep learning optimization. 
• Experience deploying machine learning models at scale in production environments.
• Familiarity with robotics systems or industrial automation hardware.
• Practical experience debugging distributed systems and optimizing network performance.
• Experience with accelerator orchestration (e.g., XManager).