Forward Deployed ML Engineer

Alexander Chapman; United States; On-site; USD 140,000 - 190,000; Full time

Job summary

Alexander Chapman is seeking a Forward Deployed ML Engineer, Benchmarks & Evaluations to help build the infrastructure behind AI evaluations and data benchmarks. You will be one of the first engineers in this high-ownership, fast-moving team, collaborating with the GM, researchers and customers to deploy repeatable evaluation products.

The role focuses on building LLM benchmarks, data pipelines, sandboxed evaluation environments, and close collaboration with customers to shape evaluation

Qualifications

• 4+ years of engineering experience.
• Comfortable in high-ambiguity, fast-moving environments.
• Strong communication and ability to work directly with customers.

Responsibilities

• Build and improve LLM/AI benchmarks and evaluation systems.
• Develop backend infrastructure for data pipelines, orchestration, storage, and execution.
• Build sandboxed environments for agentic evaluations, including tool use and code execution.
• Work directly with customers to identify evaluation needs and turn them into repeatable products.
• Partner with researchers on new datasets, benchmarks, and evaluation methodologies.

Skills

4+ years engineering experience

Job description

Building the infrastructure for AI training data and evaluations, helping frontier AI teams securely access the data they need to improve models. The team is early-stage, high-ownership, and focused on moving quickly while solving difficult technical problems.

Role — Forward Deployed ML Engineer, Benchmarks & Evaluations

You will be one of the first engineers focused on the Benchmarks & Evaluations business, working closely with the GM, researchers, and customers to build the infrastructure behind next-generation AI evaluations.

What You Will Do

• Build and improve LLM/AI benchmarks and evaluation systems
• Develop backend infrastructure for data pipelines, orchestration, storage, and execution
• Build sandboxed environments for agentic evaluations, including tool use and code execution
• Work directly with customers to identify evaluation needs and turn them into repeatable products
• Partner with researchers on new datasets, benchmarks, and evaluation methodologies

What They Are Looking For

• 4+ years of engineering experience
• Comfortable working in high-ambiguity, fast-moving environments
• Strong communication and ability to work directly with customers

Nice to have:

experience with LLM evals/benchmarks, human data pipelines, frontier AI labs, agentic systems, RL environments, or early-stage startups.