AI/ML Engineer, Individual Contributor

Join our AI/ML team to build tools that detect, evaluate, and fix failures in production AI agents. You will own the intelligence behind these systems, making AI agents more reliable for real-world applications. This role offers a unique opportunity to impact the quality and trustworthiness of AI in production.

• Detect subtle AI agent failures across large volumes of data
• Develop evaluation methods for AI detection quality, even without ground truth
• Build and verify proposed fixes for AI agent failures
• Optimize AI detection cost efficiency with appropriate models
• Hands-on experience with LLMs in production, including evaluations and LLM-as-judge
• Experience running AI agents in production and handling their failures

• No visa sponsorship is available.

• Must be authorized to work without sponsorship.