Ai Evaluation Specialist

The Big Jobsite; Aguascalientes; Remote; MXN 900,000 - 1,300,000; Full time

Job summary

Capgemini Mexico is seeking an experienced AI/ML specialist to evaluate Gemini-based AI agents and ensure responses are accurate, safe, and aligned with business goals. You will design real-world tests, analyze outputs for hallucinations and errors, and provide improvements.

You will collaborate with AI Engineers, Product Owners, and Business teams to optimize prompts, workflows, and tool integrations while safeguarding responsible AI and governance.

Qualifications

• 3+ years in AI/ML, Data Science, NLP, Conversational AI, QA Testing, Prompt Engineering, or related technical fields.
• 1+ year working with Generative AI, LLMs (Gemini, GPT, Claude, Llama), AI chatbots, RAG solutions, or AI agent evaluation.
• Experience evaluating AI responses for accuracy, relevance, groundedness, consistency, and overall business value.
• Prompt engineering and testing expertise, capable of designing evaluation scenarios, edge cases, and identifying opportunities to improve performance.
• Knowledge of AI agents, RAG, and tool-integrated workflows, including how AI systems retrieve information, reason through tasks, and interact with external tools and data sources.
• Commitment to Responsible AI and quality excellence, ensuring AI solutions meet safety, governance, authorization, and user trust requirements before production deployment.
• Fluent English level, good communication skills

Responsibilities

• Evaluate and benchmark Gemini-based AI agents to ensure responses are accurate, relevant, grounded, safe, and aligned with business objectives.
• Design and execute real-world test scenarios, including happy paths, edge cases, and adversarial prompts to identify performance gaps and risks.
• Analyze AI outputs to detect hallucinations, reasoning errors, retrieval issues, and safety concerns, then provide actionable improvement recommendations.
• Work closely with AI Engineers, Prompt Engineers, Product Owners, and Business teams to improve prompts, workflows, tool integrations, and overall agent performance.
• Own the quality and release-readiness assessment of AI solutions by defining evaluation metrics, tracking results, and supporting continuous optimization throughout pilot and production phases.

Skills

AI/ML experience

Prompt engineering

Evaluation skills

RAG workflows

Responsible AI

English fluency

Job description

Choosing Capgemini means choosing a company where you will be empowered to shape your career in the way you'd like, where you'll be supported and inspired by a collaborative community of colleagues around the world, and where you'll be able to reimagine what's possible. Join us and help the world's leading organizations unlock the value of technology and build a more sustainable, more inclusive world.

Your Role

• Evaluate and benchmark Gemini-based AI agents to ensure responses are accurate, relevant, grounded, safe, and aligned with business objectives.
• Design and execute real-world test scenarios, including happy paths, edge cases, and adversarial prompts to identify performance gaps and risks.
• Analyze AI outputs to detect hallucinations, reasoning errors, retrieval issues, and safety concerns, then provide actionable improvement recommendations.
• Work closely with AI Engineers, Prompt Engineers, Product Owners, and Business teams to improve prompts, workflows, tool integrations, and overall agent performance.
• Own the quality and release-readiness assessment of AI solutions by defining evaluation metrics, tracking results, and supporting continuous optimization throughout pilot and production phases.

Your Profile

• 3+ years in AI/ML, Data Science, NLP, Conversational AI, QA Testing, Prompt Engineering, or related technical fields.
• 1+ year working with Generative AI, LLMs (Gemini, GPT, Claude, Llama), AI chatbots, RAG solutions, or AI agent evaluation.
• Experience evaluating AI responses for accuracy, relevance, groundedness, consistency, and overall business value.
• Prompt engineering and testing expertise, capable of designing evaluation scenarios, challenging AI systems with edge cases, and identifying opportunities to improve performance.
• Knowledge of AI agents, RAG, and tool-integrated workflows, including how AI systems retrieve information, reason through tasks, and interact with external tools and data sources.
• Commitment to Responsible AI and quality excellence, ensuring AI solutions meet safety, governance, authorization, and user trust requirements before production deployment.
• Fluent English level, good communication skills

What you’ll love

• Work on meaningful projects that use technology to solve real-world challenges.
• Be part of a company that values sustainability, inclusion, and digital equity.
• Contribute to building a better future for people, planet, and society.

Need to know about the role

This role can be working from any state of Mexico.

About Capgemini

Capgemini is an AI-powered global business and technology transformation partner, delivering tangible business value. We imagine the future of organizations and make it real with AI, technology and people. With our strong heritage of nearly 60 years, we are a responsible and diverse group of over 420,000 team members in more than 50 countries. We deliver end-to end services and solutions with our deep industry expertise and strong partner ecosystem, leveraging our capabilities across strategy, technology, design, engineering and business operations. At Capgemini Mexico, we aim to attract the best talent and are committed to creating a diverse and inclusive work environment, so there is no discrimination based on race, sex, sexual orientation, gender identity or expression, or any other characteristic of a person. All applications welcome and will be considered based on merit against the job and/or experience for the position.