OverviewWe are seeking a
Senior AI Safety Engineer specializing in AI Safety to lead adversarial testing, risk assessment, and safety evaluations for
LLM- and agent-powered chatbot systems. This role focuses on ensuring that AI technologies are safe, reliable, and aligned with business and user needs across high-impact use cases.
You will join a collaborative interdisciplinary team to design, evaluate, and harden AI/ML systems against misuse, failures, and emerging risks. You will work closely with product owners, engineering teams, and business stakeholders to identify safety requirements, conduct adversarial assessments, and develop robust mitigation strategies. This role is highly technical and safety-critical, with broad visibility and influence across the organization.
ResponsibilitiesAI Safety, Robustness & Risk Assessment- Lead adversarial testing, including jailbreak attempts, prompt injection, harmful content generation, system-prompt extraction, and agent-tool misuse.
- Conduct end-to-end risk assessments for AI-driven chatbots and autonomous agent systems, identifying hazards, evaluating exposure, and defining mitigation strategies.
- Build and maintain AI safety evaluation pipelines, including red-team test suites, scenario-based evaluations, and automated stress testing.
- Define and monitor safety KPIs such as harmful output rates, robustness scores, and model resilience metrics.
- Analyze failure modes (e.g., hallucinations, deceptive reasoning, unsafe tool execution) and design guardrails to minimize risks.
Technical Development & Collaboration- Develop reproducible experiments for LLM behavior analysis, including prompt engineering, control mechanisms, and guardrail testing.
- Partner with data engineers and MLOps teams to integrate safety evaluations into CI/CD pipelines.
- Work with product teams to translate safety requirements into actionable technical specifications.
- Support model governance, including documentation, safety reports, and compliance with internal and external standards.
- Contribute to innovation and research around emerging safety methodologies for LLMs and agent architectures.
Knowledge Sharing & Leadership- Serve as an internal expert on AI safety best practices, adversarial testing methodologies, and robust system design.
- Provide guidance and mentorship to data scientists, engineers, and product partners on safe AI development.
- Create high-quality documentation, playbooks, and reusable tools for safety evaluations.
Compensation and Benefits:- The expected compensation range for this position is between $89,000 - $149,000.
- Location, confirmed job-related skills, experience, and education will be considered in setting actual starting salary. Your recruiter can share more about the specific salary range during the hiring process.
- Bonus based on performance and eligibility target payout is 10% of annual salary paid out annually.
- Paid time off subject to eligibility, including paid parental leave, vacation, sick, and bereavement.
- In addition to salary, PepsiCo offers a comprehensive benefits package to support our employees and their families, subject to elections and eligibility: Medical, Dental, Vision, Disability, Health, and Dependent Care Reimbursement Accounts, Employee Assistance Program (EAP), Insurance (Accident, Group Legal, Life), Defined Contribution Retirement Plan.
Qualifications- Master's degree in Computer Science, Data Science, Machine Learning, or related quantitative field.
- 4+ years of experience developing or evaluating machine learning systems, including LLM- or NLP-based applications.
- Strong knowledge of Generative AI and Transformer-based models.
- Experience with at least one deep learning framework (PyTorch, TensorFlow).
- Proficiency with Python and common data/ML libraries.
- Experience conducting model evaluations, experimentation, or reliability testing.
- Clear communication skills and the ability to translate technical findings into business-relevant insights.
Preferred Qualifications- Experience with adversarial ML, red-teaming, or AI safety research.
>Our Company will consider for employment qualified applicants with criminal histories in a manner consistent with the requirements of the Fair Credit Reporting Act, and all other applicable laws, including but not limited to, San Francisco Police Code Sections 4901-4919, commonly referred to as the San Francisco Fair Chance Ordinance; and Chapter XVII, Article 9 of the Los Angeles Municipal Code, commonly referred to as the Fair Chance Initiative for Hiring Ordinance.
All qualified applicants will receive consideration for employment without regard to age, race, color, religion, sex, sexual orientation, gender identity, national origin, protected veteran status, or disability status.
PepsiCo is an Equal Opportunity Employer: Female / Minority / Disability / Protected Veteran / Sexual Orientation / Gender Identity
If you'd like more information about your EEO rights as an applicant under the law, please download the available EEO is the Law & EEO is the Law Supplement documents. View PepsiCo EEO Policy.
Please view our Pay Transparency Statement
Never miss an opportunity! Create an alert based on the job you applied for.
