Research Engineer

Job Opportunity At KovariKovari develops frontier technology to transform physical businesses. They partner with established operators to change how they run, and build and operate businesses of their own through their subsidiaries.Kovari is a small team of builders, operators, and researchers. They deploy on-site alongside the businesses they serve and iterate in the field.

The company has raised over $6M from leading investors and is based in San Francisco.The OpportunityYou will research and ship manipulation policies that work reliably in the field. You own the loop from data to model to deployment, and you see your policies run on robots in live operations.What You'll DoResearch and develop high-reliability manipulation policies built for fast deployment and iterationOperate in a fast data flywheel across multiple modalitiesDeep debug failure modes in transformer and diffusion policies deployed in the fieldOptimize policies for real-time inference on edge hardwareYou Should HaveExperience deploying robot policies on hardware, including model-based, RL, or imitation learning approachesSim-to-real or real robot data experienceExperience with multimodal inputs including vision, depth, force/torque, and proprioceptionExperience with edge inference optimization using TensorRT, ONNX Runtime, or TVMExperience with CUDA kernel optimizationA bias toward action: train fast, deploy early, learn from failureNice To HavePublications at CoRL, RSS, ICRA, NeurIPS, or similar venues