At Rhoda AI, we're building the full-stack foundation for the next generation of humanoid robots — from high-performance, software-defined hardware to the foundational models and video world models that control it. Our robots are designed to be generalists capable of operating in complex, real-world environments and handling scenarios unseen in training. We work at the intersection of large-scale learning, robotics, and systems, with a research team that includes researchers from Stanford, Berkeley, Harvard, and beyond. We're not building a feature; we're building a new computing platform for physical work — and with over $400M raised, we're investing aggressively in the R&D, hardware development, and manufacturing scale-up to make that a reality.
We're looking for an ML Infrastructure Engineer to help build and operate the inference systems that power our automation stack. You'll be responsible for running large foundation models efficiently and reliably, integrating closely with our robot platform and internal task tooling.
What You'll Do
Build and maintain infrastructure to run model inference across cloud and on-prem environments
Optimize latency, throughput, and reliability of deployed models
Design and scale services to serve various foundation models across research and production use cases
Work closely with research and robotics teams for inference optimization and integration
Build tooling for model deployment, versioning, and observability to support fast iteration cycles
Contribute to the reliability and scalability of the inference stack as model complexity and deployment footprint grow
What We're Looking For
3+ years of experience in ML infrastructure, MLOps, or backend systems
Experience deploying and managing ML inference workloads in production
Strong proficiency with Kubernetes and containerized deployment pipelines
Experience with cloud providers (e.g., AWS, GCP) and GPU orchestration
Familiarity with common ML frameworks (e.g., PyTorch, TensorFlow) and model serving tools (e.g., Triton, TorchServe, Ray Serve)
Strong debugging instincts and ownership mentality — comfortable driving issues to resolution across the stack
Nice to Have (But Not Required)
Experience optimizing inference performance (e.g., quantization, batching, caching)
Familiarity with multimodal or large foundation models
Exposure to real-time systems, robotics, or edge/cloud hybrid deployment patterns
Interest in building tooling for model deployment, observability, and version control
Experience with on-robot or edge inference and the latency constraints that come with it
Why This Role
Own the inference layer that connects our foundation models to real robot behavior — a direct line between your work and what the robot does in the world
Be part of building the infrastructure stack for one of the most technically ambitious robotics companies in the world
