Senior Software Engineer - ML Infrastructure

We're looking for a Senior Software Engineer - ML Infrastructure to build and scale the infrastructure that powers our AI-driven warehouse intelligence platform. You'll own the end-to-end lifecycle of computer vision models - from training pipelines through optimized cloud deployment - ensuring our cutting-edge computer vision and multi-modal AI systems run reliably and efficiently in production.

Your work will directly enable the real-time perception and autonomous decision-making capabilities at the core of our platform.

This is a deeply technical role at the intersection of machine learning, distributed systems, and cloud infrastructure. You'll design scalable GPU compute clusters, build robust orchestration pipelines, and optimize model serving for low-latency inference at scale. You'll work closely with our research scientists, computer vision engineers, and product teams to bridge the gap between experimental models and production-ready systems that operate across diverse warehouse environments.

We've found tremendous value in collaborative problem-solving, thus our team works from our SF office three days a week.

- Develop and maintain distributed cloud GPU infrastructure for large-scale world model training and low-latency inference.

- Build end-to-end computer vision pipelines - from data ingestion and preprocessing through model training, evaluation, and deployment - and integrate them into core product workflows.

- Deploy and optimize state-of-the-art machine learning models in the cloud using model serving platforms and inference optimization techniques, including VLMs and VLAs.

- Design and operate orchestration systems that enable both engineers and non-engineers to build and manage data and ML pipelines.

- Establish monitoring, benchmarking, and evaluation frameworks to ensure model performance and reliability in production environments.

- B.S. / M.S. in Computer Science, Robotics, or similar technical field, or equivalent practical experience.

- 7+ years of professional software engineering experience, with at least 3 years in machine learning infrastructure - developing, scaling, training, deploying, and optimizing large-scale ML systems from data to model.

- Track record of deploying machine learning models in production environments with real-world constraints.

- Experience with distributed messaging and compute systems (Kafka, gRPC, ROS2, or similar).

- Strong programming skills in Python with solid software engineering practices.

- Experience with training and/or deployment of machine learning models in the computer vision domain.

- Experience developing, running, and managing orchestration systems (Flyte, Temporal, Airflow, or similar) for ML and data pipelines.

- Proficiency with ML frameworks (PyTorch, TensorFlow, DeepSpeed) and model serving platforms (TorchServe, TensorFlow Serving, NVIDIA Triton Inference Server, or similar).

- Deep understanding of state-of-the-art machine learning models such as auto-regressive transformers and familiarity with inference optimization techniques (TensorRT, quantization, custom kernels).

- Experience with C++ or CUDA programming for GPU acceleration.

- Prior experience working at autonomous vehicles or robotics companies.