Robotics Research Assistant
Artificial Analysis
Robotics Research Assistant
Artificial Analysis
Independent AI model and API benchmarks
Location: San Francisco, California — on-site
Artificial Analysis is the leading independent AI benchmarking company. We support labs, engineers, and enterprises to understand AI capabilities and make critical decisions about their AI strategies. We are the go-to authority for understanding AI, from AI labs and enterprises to media, investors, and policymakers. Our benchmarks don’t just measure the cutting edge of AI; they are actively shaping the frontier.
Our benchmarks and analysis are trusted by hundreds of thousands of users and are the go-to reference for leading AI labs including OpenAI, Google, Meta, NVIDIA, and Anthropic, and major publications including the Wall Street Journal, Bloomberg, the Financial Times, and The Economist.
We are a team of 50+, on track to double by year end, backed by Nat Friedman, Daniel Gross, Andrew Ng, Adam D’Angelo, Clem Delangue, and other industry leaders.
The physical world is where the next generation of AI models will compete. We’re developing our robotics benchmarks to set the industry’s reference point: testing how AI models perform on physical robots and in simulation, and building the analysis that helps the industry understand them.
As a Robotics Research Assistant, you’ll work closely with our robotics researchers and engineers to run benchmarks and keep our robots built, calibrated, tested, and running. You’ll help build and maintain hardware, run our task suite, and set up new simulation environments as we add them.
This is a hands-on lab and benchmark-operations role. It suits a recent graduate or early-career candidate with substantial practical hardware experience who enjoys building, troubleshooting, and carefully running experiments. Expect to spend much of the day setting up, resetting, and monitoring trials.
Build and maintain an evolving suite of hardware. Power, wire, and health-check hardware so each station is ready to run. Work efficiently to understand unfamiliar hardware and incorporate it into our fleet.
Run the task suite and read the results. Set up task scenes, run startup and shutdown checks, and monitor trials on physical robots and in simulation.
Protect result quality. Check that recordings and logs are complete and linked to the right task, model, and configuration. Record interventions and distinguish model failures from equipment, setup, or simulation faults.
Maintain the hardware. Assemble hardware, route cables, mount fixtures and cameras, calibrate equipment, manage spare parts, and make the small mechanical fixes that keep a fleet running.
Keep the lab ready. Carry out routine checks and maintenance, organize tools and spares, and follow lab safety procedures.
Improve how the lab runs. Keep operating instructions current, flag recurring problems, and, where your skills allow, contribute fixtures, 3D-printed parts, or scripts.
A recent graduate or early-career background in robotics, mechatronics, mechanical engineering, electrical engineering, or a related field, with substantial hands-on hardware experience from labs, projects, internships, or similar practical work. We do not require two years of professional experience for this posting.
Evidence that you have built, operated, maintained, or troubleshot robots, lab equipment, or electromechanical systems yourself.
Practical troubleshooting: you can investigate a fault, test likely causes with appropriate tools, and explain what you learned.
Careful execution of multi-step procedures, with strong attention to detail and reliable records.
The ability to develop toward independently running a full day of trials after training, resolving routine problems, and recognizing when to ask for help.
Clear communication and teamwork with researchers and engineers.
Confidence picking up unfamiliar tools and software workflows.
3D printing experience, including through university or personal projects.
ROS 2, Isaac Sim, MuJoCo, or another simulator you’ve debugged rather than just launched.
Experience running benchmark or test campaigns where the count and ordering of trials matter.
Recent graduates are welcome to apply. We are a small, growing team working on one of the most interesting problems in AI. You do not need to tick every box. If you are curious and keen to learn, we will support you to develop your practical skills and take on more responsibility.
Shape how AI gets built. Leading AI labs track our benchmarks and use them to guide their development priorities. Your work will help the industry understand how AI performs in the physical world.
Build expertise in frontier AI and robotics. Work closely with researchers and engineers evaluating AI models on physical robots and in simulation.
Join at a defining moment. We’re 50+ people, on track to double by year end, backed by some of the most connected investors in AI. The people who join now will shape the product, team, and strategy as we scale.
Competitive compensation.
Independent AI model and API benchmarks
Independent benchmarking and analysis of AI models and API hosting providers, with benchmarks and leaderboards across intelligence, coding agents, image/speech/video, and inference metrics to help teams choose the right model and provider. It publishes data-driven reports like Intelligence Index releases, capability indexes, and trend analyses, packaging benchmarks as insights and data products for AI buyers. Unlike others, it does not host or sell models, focusing on unbiased evaluation and transparent metrics. The goal is to help AI buyers understand the landscape and select AI models and API providers that fit their use case.
Explore more opportunities at Artificial Analysis