Senior ML Engineer – AI Safety
São Carlos, SP, Brazil
- Pay
- Salary not listed in the saved posting
- Work setup
- Unconfirmed
- Employment
- Unconfirmed
What you’ll work on
Full postingLead the design and implementation of Responsible AI frameworks, governance policies, and safety guardrails for GenAI systems.
Define and own AI safety evaluation pipelines, including red-teaming, adversarial robustness testing, jailbreak and prompt injection assessments, and automated safety benchmarks.
Develop explainability and interpretability tooling to support model audits, regulatory reviews, and clear communication of model behaviour and limitations.
From the employer’s posting
Key responsibilities Lead the design and implementation of Responsible AI frameworks, governance policies, and safety guardrails for GenAI systems. Define and own AI safety evaluation pipelines, including red-teaming, adversarial robustness testing, jailbreak and prompt injection assessments, and automated safety benchmarks.
Lead the design and implementation of Responsible AI frameworks, governance policies, and safety guardrails for GenAI systems. Define and own AI safety evaluation pipelines, including red-teaming, adversarial robustness testing, jailbreak and prompt injection assessments, and automated safety benchmarks. Develop explainability and interpretability tooling to support model audits, regulatory reviews, and clear communication of model behaviour and limitations.
Define and own AI safety evaluation pipelines, including red-teaming, adversarial robustness testing, jailbreak and prompt injection assessments, and automated safety benchmarks. Develop explainability and interpretability tooling to support model audits, regulatory reviews, and clear communication of model behaviour and limitations. Partner with risk, compliance, legal, privacy, security, product, and engineering teams to embed safety requirements into scalable GenAI solutions.
What you’ll bring
All qualificationsCore experience
- Experience in machine learning, data science, or software engineering, including focused on AI safety, alignment, Responsible AI, or model governance.
- Experience designing or running automated benchmark suites for LLMs or other GenAI systems.
- Strong Python skills and proficiency with ML frameworks such as TensorFlow, PyTorch, scikit-learn, or equivalent tooling.
- Familiarity with bias detection, harm classification, content safety tooling, or policy evaluation frameworks.
- Demonstrated knowledge of AI safety techniques including red-teaming, adversarial testing, fairness metrics, interpretability methods, and alignment approaches.
- Experience with regulated financial services use cases such as fraud detection, credit risk, customer service automation, or model risk management.
Preferred experience
- Strong understanding of AI governance, model risk management, and regulatory expectations in financial services, with practical experience preparing documentation for audit or regulatory review preferred.
Qualification wording
Experience in machine learning, data science, or software engineering, including focused on AI safety, alignment, Responsible AI, or model governance.
Experience designing or running automated benchmark suites for LLMs or other GenAI systems.
Strong Python skills and proficiency with ML frameworks such as TensorFlow, PyTorch, scikit-learn, or equivalent tooling.
Familiarity with bias detection, harm classification, content safety tooling, or policy evaluation frameworks.
Demonstrated knowledge of AI safety techniques including red-teaming, adversarial testing, fairness metrics, interpretability methods, and alignment approaches.
Experience with regulated financial services use cases such as fraud detection, credit risk, customer service automation, or model risk management.
Strong understanding of AI governance, model risk management, and regulatory expectations in financial services, with practical experience preparing documentation for audit or regulatory review preferred.
Tools in this posting
- Python
- MLflow
- PyTorch
- TensorFlow
- scikit-learn
Source — Tool mentions in context
- Experience in machine learning, data science, or software engineering, including focused on AI safety, alignment, Responsible AI, or model governance. - Strong Python skills and proficiency with ML frameworks such as TensorFlow, PyTorch, scikit-learn, or equivalent tooling. - Hands-on MLOps experience, including MLflow, Kubeflow, CI/CD for ML, model monitoring, versioning, and reproducible deployment practices.
- Strong Python skills and proficiency with ML frameworks such as TensorFlow, PyTorch, scikit-learn, or equivalent tooling. - Hands-on MLOps experience, including MLflow, Kubeflow, CI/CD for ML, model monitoring, versioning, and reproducible deployment practices. - Demonstrated knowledge of AI safety techniques including red-teaming, adversarial testing, fairness metrics, interpretability methods, and alignment approaches.
Posting record
Report an error- Status in our records
- Live
- First seen by us
- Oct 1, 2026 · 15d ago
- Recorded sightings
- 129
- Last seen by us
- Oct 15, 2026
These dates show when we found the listing. Check the employer’s website to confirm it is still accepting applications.
Job description
Job Description
We are looking for an experienced, proactive Senior ML Engineer to join Experian’s AI Safety team. You will lead the design, implementation, and governance of safety-critical GenAI systems across the business, partnering with senior engineers, security, risk, compliance, legal, and product stakeholders to ensure AI systems are robust, explainable, fair, auditable, and aligned with regulatory and ethical standards. As a senior contributor, you will mentor engineers, shape technical strategy, and help drive adoption of AI safety best practices across the organisation.
Key responsibilities
Lead the design and implementation of Responsible AI frameworks, governance policies, and safety guardrails for GenAI systems.
Define and own AI safety evaluation pipelines, including red-teaming, adversarial robustness testing, jailbreak and prompt injection assessments, and automated safety benchmarks.
Develop explainability and interpretability tooling to support model audits, regulatory reviews, and clear communication of model behaviour and limitations.
Partner with risk, compliance, legal, privacy, security, product, and engineering teams to embed safety requirements into scalable GenAI solutions.
Lead incident response and root cause analysis for AI-related safety issues, including post-incident reviews and remediation playbooks.
Contribute to GenAI-powered solutions in fraud detection, credit risk, customer service automation, and platform initiatives while ensuring alignment with AI risk appetite.
Mentor junior and mid-level engineers and represent AI Safety in cross-functional forums.
Qualifications
Required qualifications
Experience in machine learning, data science, or software engineering, including focused on AI safety, alignment, Responsible AI, or model governance.
Strong Python skills and proficiency with ML frameworks such as TensorFlow, PyTorch, scikit-learn, or equivalent tooling.
Hands-on MLOps experience, including MLflow, Kubeflow, CI/CD for ML, model monitoring, versioning, and reproducible deployment practices.
Demonstrated knowledge of AI safety techniques including red-teaming, adversarial testing, fairness metrics, interpretability methods, and alignment approaches.
Strong understanding of AI governance, model risk management, and regulatory expectations in financial services, with practical experience preparing documentation for audit or regulatory review preferred.
Excellent written and verbal English skills, with the ability to translate complex safety concepts for non-technical audiences.
Nice-to-have
Experience designing or running automated benchmark suites for LLMs or other GenAI systems.
Familiarity with bias detection, harm classification, content safety tooling, or policy evaluation frameworks.
Experience with regulated financial services use cases such as fraud detection, credit risk, customer service automation, or model risk management.
Experience influencing engineering standards or mentoring engineers in AI safety, Responsible AI, or production ML practices.
Additional Information
At Serasa Experian, we believe that diversity is essential for a healthier and more innovative work environment, where everyone can share experiences and express their ideas. That’s why we promote several initiatives to support inclusive recruitment and the professional development of our people.
We also have our affinity groups, created to empower and support individuals from underrepresented groups: ExperianPride (LGBTQIAPN+ community), Ubuntu (racial equity), Women in Experian (gender equity), Aspire (people with disabilities), and Connecting Generations (generations).
Come be part of this transformation!
Experian Careers - Creating a better tomorrow together
Find out what its like to work for Experian by clicking here
Company Description
Experian is a global data and technology company that drives opportunities for people and businesses around the world. We operate in diverse markets such as financial services, healthcare, automotive, agribusiness, insurance, and more. Experian invests in people and advanced new technologies to unlock the power of data. We have an incredible team of 25,200 employees in 32 countries.
Our uniqueness is valuing yours. Experian's people-centric, inclusive, and purpose-driven culture is recognized by numerous awards — including World’s Best Workplaces™ 2025 (Fortune's Top 25 global) and Great Place To Work™ in 26 countries, among others. Check out Experian Life on social media or explore our careers website to understand why. Experian is also proud to be an equal opportunity employer and an affirmative action employer. If you have a disability or need that requires accommodation, please let us know as soon as possible.
Your next step
- Have your CV and examples of relevant work ready.
- Check the listed location, eligibility and core experience before starting.
- Ask the employer about the salary range before committing time to the process.
Complete your application on jobs.smartrecruiters.com. The employer’s form will show what is required.
Already applied? Track this application
Source details
Source notes
Source excerptsSelected passages from the saved posting. Check the full description for conditions and exceptions.
- Pay
No pay amount identified in the saved description.
- Location & working pattern
São Carlos, SP, Brazil
Working pattern and location restrictions need checking in the full posting.
- Work authorization
No clear work-authorization passage found. Eligibility is unconfirmed.
See how this role fits your experience
Add your resume to compare the role’s scope, tools and requirements with your experience.