Responsible AI / Eval Specialist

Position Title:Responsible AI / Eval Specialist
Position Type: Regular - Full-Time
Requisition ID:43986
- Design and execute evaluation strategies for AI use cases, including assessments of accuracy, reliability, hallucination rates, fairness, and robustness.
- Build, maintain, and operate evaluation harnesses, benchmark suites, and golden datasets across the McCain AI technology stack.
- Conduct stage-gate evaluations and provide clear, actionable findings to support governance decisions.
- Run bias and fairness testing across protected attributes and business-relevant user groups.
- Identify, quantify, and communicate fairness concerns while recommending practical remediation approaches.
- Lead red-team and adversarial testing exercises to identify vulnerabilities, failure modes, prompt injection risks, and jailbreak scenarios.
- Partner with Enterprise Security teams to strengthen AI resilience through broader adversarial testing initiatives.
- Support risk classification activities by providing evaluation evidence and recommendations that inform governance decisions.
- Collaborate with AI Platform & Engineering and Knowledge Engineering teams to embed evaluation capabilities into AI development workflows.
- Maintain model cards, evaluation reports, decision logs, and other governance documentation while contributing to Responsible AI standards and playbooks.
- Coach AI Engineers and Forward Deployment Engineers on evaluation best practices and quality disciplines.
- Share evaluation insights, frameworks, and reusable patterns across the AI organization.
- Bachelor's degree in Computer Science, Statistics, Engineering, or a related field; advanced degree preferred.
- 10+ years of experience in AI/ML evaluation, model validation, model risk management, or a related discipline.
- Hands-on experience with AI/ML evaluation methodologies and performance metrics, including accuracy, calibration, fairness, and robustness.
- Experience evaluating Large Language Models (LLMs) and AI agents using frameworks such as HELM, Eleuther LM Evaluation Harness, or equivalent platforms.
- Strong Python programming skills and experience with common machine learning evaluation and testing tools.
- Experience working with Databricks or comparable enterprise data platforms.
- Familiarity with Responsible AI and AI governance frameworks, including NIST AI RMF, EU AI Act, ISO/IEC 42001, or similar standards.
- Strong analytical, problem-solving, and critical-thinking skills.
- Ability to communicate complex technical findings effectively to both technical and non-technical stakeholders.
- Experience conducting bias testing, red-team exercises, adversarial testing, and AI risk assessments is highly desirable.
McCain Foods is an equal opportunity employer. As a global family-owned company, we strive to be the employer of choice in the diverse communities around the world in which we live and work. We recognize that inclusion drives our creativity, resilience, and success and makes our business stronger. All qualified applicants will receive consideration for employment without regard to race, religion, color, national origin, sex, age, veteran status, disability, or any other protected characteristic under applicable law.
McCain is an accessible employer. If you require an accommodation throughout the recruitment process (including alternate formats of materials or accessible meeting rooms), please let us knowand we will work with you to find appropriate solutions.
Your privacy is important to us. By submitting personal data or information to us, you agree this will be handled in accordance with McCain's Global Privacy Policyand Global Employee Privacy Policy, as applicable. McCain leverages AI in the hiring process, though all final decisions are made by humans. You can understand our approach to AI and how your personal information is being handled here.
Job Family:Information Technology
Location(s): IN - India : Haryana : Gurgaon
Company:McCain Foods(India) P Ltd
Employment Type: OTHER