Copy of AI Model Testing Engineer

CoVet

11d•Remote

About The Position

We are looking for a scrappy, creative, and detail-oriented AI Model Testing Engineer to build, manage, and continuously enhance our infrastructure for testing and evaluating AI models from leading providers such as OpenAI, Google, and Anthropic. This role will have a particular focus on LLMs & transcription model testing and optimization. You’ll collaborate closely with our medical team to craft targeted test cases, enabling veterinarians to identify and select the most accurate and effective AI-generated outputs.

Requirements

Demonstrable experience building and shipping software or projects that incorporate AI models (LLMs and/or transcription models), with specific examples of past work.
Experience or familiarity with AI model integration.
Proficiency with Node.js and TypeScript.
Familiarity with APIs from providers such as OpenAI, Google, or Anthropic.
Excellent problem-solving skills with a scrappy, innovative mindset—able to devise effective solutions under resource constraints.
Strong collaboration and communication skills to effectively partner with cross-functional teams, including medical professionals.

Responsibilities

Design, develop, and maintain testing pipelines and logic primarily focused on transcription models, while also covering other AI models such as LLMs and real-time inference models.
Collaborate closely with the veterinary medical team to translate clinical scenarios into structured transcription and AI model test cases.
Implement frameworks for comparative analysis, allowing veterinarians to systematically review and select optimal AI outputs.
Balance and optimize accuracy, quality, speed, and cost-efficiency of AI model usage.
Manage end-to-end infrastructure for AI model testing and experimentation, ensuring scalability and reliability.
Continuously identify creative solutions to enhance AI performance and usability based on testing feedback and outcomes.