AI Evaluation Specialist

Metas Solutions excels in providing strategic consulting, program management, and data-driven analytics to federal public health agencies. Our expertise enhances health systems and delivers measurable outcomes, helping agencies achieve their mission. We collaborate with federal partners to implement agile solutions for national public health initiatives, driving impactful changes through cutting-edge programs that strengthen communities and promote well-being. See  for further details about us and careers with Metas.

Metas Solutions has an "immediate opening" for a talented AI Evaluation Specialist to evaluate enterprise AI tools and capabilities to determine their effectiveness, safety, usability, and readiness for business adoption. In this Remote position, you’ll partner with product managers, data scientists, AI engineers, software engineers, security and privacy teams, and business stakeholders to define evaluation criteria and conduct structured assessments of generative AI products and platforms, including tools such as OpenAI and life sciences models like Rosalind.

You will design repeatable evaluation frameworks, test real-world use cases, analyze model and product behavior, and translate findings into clear recommendations. You will be responsible for comparing AI solutions across quality, accuracy, reliability, safety, privacy and security.

• Plan and execute hands-on evaluations of AI tools such as OpenAI and life sciences models like Rosalind using representative business scenarios, workflows, prompts, datasets, and user personas
• Assess AI solutions for response quality, factual accuracy, relevance, consistency, reasoning, instruction following, reliability, latency, usability, accessibility, and overall task effectiveness
• Design and maintain standardized evaluation frameworks, scorecards, rubrics, and acceptance criteria for enterprise AI tools, models, agents, and AI-enabled applications
• Evaluate safety, privacy, security, data handling, governance, and responsible AI considerations in collaboration with security, privacy, legal, and governance stakeholders
• Conduct comparative evaluations and proof-of-concept assessments across multiple AI products, models, configurations, and vendors, including analysis of functionality, integration requirements, performance, and cost
• Evaluate AI agents and tool-enabled workflows, including retrieval-augmented generation (RAG), enterprise search, file and data analysis, connectors, APIs, and Model Context Protocol (MCP)-enabled capabilities where applicable
• Stay current with advancements in generative AI, model evaluation, AI safety, responsible AI, and emerging enterprise AI products and incorporate relevant methods into the evaluation program
• Engage in knowledge sharing and contribute to building a strong, collaborative team environment

• 5+ years of experience in model evaluation, model quality assurance with hands-on experience evaluating AI-enabled products or services
• Experience developing structured evaluation plans, test cases, scoring rubrics, benchmarks, and measurable acceptance criteria
• Experience with hands-on generative AI tools and large language models, including prompt design, systematic testing, output analysis, and identification of hallucinations and other failure modes
• Experience assessing AI systems across dimensions such as accuracy, relevance, consistency, safety, bias, privacy, security, usability, performance, and cost
• Ability to demonstrate familiarity with common generative AI architectures and capabilities, including large language models, retrieval-augmented generation (RAG), AI agents, APIs, enterprise search, and tool or connector integrations
• Bachelor's degree
• Must be a U.S. Citizen or Lawful Permanent Resident (Green Card Holder)

• Experience evaluating enterprise AI platforms or assistants, including OpenAI products and life sciences models like Rosalind or comparable generative AI solutions
• Experience with automated LLM evaluation frameworks, model-as-a-judge approaches, human-in-the-loop evaluation, red teaming, or adversarial testing
• Experience evaluating RAG systems, AI agents, MCP-enabled tools, enterprise connectors, or multi-step AI workflows
• Experience developing dashboards or reporting mechanisms for AI evaluation metrics, quality trends, risk findings, and regression results
• Ability to work with datasets and evaluation results using tools such as Python, SQL, spreadsheets,…