Robotics ML Engineer: Edge & Real-World Training

a16z-speedrun; San Francisco (CA); On-site; USD 150,000 - 230,000; Full time

Job summary

a16z-speedrun is seeking a robotics ML researcher to own the loop from raw robot data to a deployed model on real hardware. You will train multimodal models, optimize inference, and test on real robots, bridging research and production systems.

You’ll work across vision, language, proprioception, and control data, with a focus on robust evaluation, edge deployment, and fast iteration in hardware-in-the-loop experiments.

Qualifications

• You have trained modern vision, transformer, diffusion, generative, or multimodal models.
• You are highly productive in PyTorch, JAX, or a comparable ML stack.
• You understand both model behavior and the systems required to train and deploy models reliably.
• You have experience with distributed training, large datasets, inference optimization, or GPU performance.
• You can move comfortably between research code, data pipelines, production services, and edge deployment.
• You are excited by messy real-world data and do not require a perfectly clean benchmark before beginning.
• You have strong experimental judgment and can distinguish genuine improvement from an attractive demo.

Responsibilities

• Train multimodal models over video, language, proprioception, motor currents, force, tactile, IMU, telemetry, trajectories, and policy traces.
• Build models for anomaly detection, episode scoring, failure classification, incident understanding, representation learning, and behavioral evaluation.
• Integrate, evaluate, adapt, or fine-tune vision-language-action models and other robot policies across different embodiments.
• Develop training and evaluation methods for limited, noisy, heterogeneous, and highly imbalanced real-world robot data.
• Turn failures, operator takeovers, recoveries, and successful episodes into evals, labeled datasets, and training signals.
• Distill, quantize, prune, compile, and optimize models for deployment on constrained edge hardware.
• Design benchmarks, ablations, fault-injection experiments, and metrics that tell us whether a model will actually improve real-world operation.
• Work closely with the infrastructure team on distributed training and data systems, and with the edge team on low-latency inference.
• Validate ideas in simulation and then close the loop on physical robots.

Skills

PyTorch

JAX

Multimodal models

Edge deployment

Distributed training

GPU performance

Tools

TensorRT

ONNX

Triton

CUDA

Isaac Sim

MuJoCo

ManiSkill

Job description

a16z-speedrun is seeking a robotics ML researcher to own the loop from raw robot data to a deployed model on real hardware. You will train multimodal models, optimize inference, and test on real robots, bridging research and production systems.

You’ll work across vision, language, proprioception, and control data, with a focus on robust evaluation, edge deployment, and fast iteration in hardware-in-the-loop experiments.