Member of Technical Staff (Applied AI Research

Job Description – Member of Technical Staff (Applied AI Research)

Location:

San Francisco (on-site at our offices)
About Artificial Analysis

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 40+, on track to double by end of year, backed by Nat Friedman (Git Hub, Meta), Daniel Gross (SSI, Meta), Andrew Ng (Google Brain, Deep Learning.ai, Amazon), Adam D’Angelo (Quora, Poe, OpenAI), Clem Delangue (Hugging Face) and other industry leaders.

Our evaluations decide how the world measures AI. When a frontier lab ships a model, our benchmarks are how the industry finds out what it can actually do, and the labs themselves use our results to guide what they build next. This role puts you on the measurement frontier: you won’t just observe the cutting edge, your work will define what cutting edge means.

We’re hiring Members of Technical Staff (Applied AI Research) to design the evaluations that set the standard for how AI is measured: building novel benchmarks and datasets, evaluating every major model as it releases, working with the frontier labs on pre-release models before the world sees them, and publishing the analysis that labs, enterprises, media and policymakers rely on. The bar for success is becoming a world expert in modern AI.

This is applied research with immediate industry consequence: shorter cycles than academia, more rigor than industry commentary, and a bigger audience than both. The center of the role is building: the large majority of your time goes to designing and shipping evaluations, with analysis and industry collaboration built around that work.

• Design Frontier Evaluations: Conceive, build and ship novel evaluation methodologies that advance how AI capabilities are measured, and that stay ahead of what frontier models can do
• Build Evaluation Datasets and Infrastructure: Construct the datasets, harnesses and scoring systems behind our benchmarks, engineered for contamination resistance and repeatability at frontier scale
• Evaluate Every Major Model: Run our evaluation suite across frontier releases as they land, and own the integrity of the results the industry quotes
• Publish Influential Analysis: Produce the reports, indexes and data visualizations that shape how labs, enterprises and the broader industry understand AI progress
• Work with Frontier Labs on Pre-Release Models: Benchmark the leading labs’ systems, including pre-release and newly launched models, working directly with their research teams; our commercial team owns client relationships day to day, so your time stays on the science
• Become AI-Native: Embrace an AI-native workflow, using cutting-edge AI tools to generate leverage in a fast-changing industry and maintain our competitive edge in AI benchmarking

We require 3+ years of relevant professional experience, across industry or research. You have an intense interest in AI, a desire to become a world expert in the field, and strong analytical and coding skills to back it up.

Beyond that bar, we hire from three backgrounds. You should clearly fit one of these profiles:

Backgrounds include: ML Engineer, ML Researcher, Research Engineer, AI Engineer, Forward Deployed Engineer, Technical PM, or similar roles at AI companies or AI-focused teams.

You have hands-on experience with modern AI systems and understand how models work at a technical level. You want your work to ship faster than a paper and matter more than a dashboard: evaluations the whole industry…