Senior ML Engineer – AI Safety

This is a fully remote position, open to applicants in Mali, +1 more country.

📋 Description

• Oversee the design and execution of Responsible AI frameworks, governance policies, and safety measures for GenAI systems.

• Establish and manage AI safety evaluation processes, which include red-teaming, adversarial robustness testing, assessments of jailbreak and prompt injection, as well as automated safety benchmarks.

• Create tools for explainability and interpretability to facilitate model audits, regulatory evaluations, and the communication of model behavior and limitations.

• Collaborate with risk, compliance, legal, privacy, security, product, and engineering teams to incorporate safety requirements into scalable GenAI solutions.

• Direct incident response and root cause analysis for AI-related safety concerns, including post-incident evaluations and remediation strategies.

• Contribute to GenAI-driven solutions in areas such as fraud detection, credit risk management, customer service automation, and platform development initiatives.

• Mentor junior and mid-level engineers and serve as a representative for AI Safety in cross-functional discussions.

• Influence technical strategy and promote the adoption of AI safety best practices throughout the organization.

⛳️ Requirements

• Background in machine learning, data science, or software engineering, with a focus on AI safety, alignment, Responsible AI, or model governance.

• Strong proficiency in Python.

• Expertise in ML frameworks such as TensorFlow, PyTorch, scikit-learn, or similar tools.

• Practical experience in MLOps, including MLflow, Kubeflow, CI/CD for ML, model monitoring, version control, and reproducible deployment methodologies.

• Understanding of AI safety methods, including red-teaming, adversarial testing, fairness metrics, interpretability techniques, and alignment strategies.

• Solid grasp of AI governance, model risk management, and regulatory requirements in the financial sector.

• Exceptional written and verbal communication skills in English.

• Advanced English proficiency with regular interaction with global teams.

• Preferred experience in preparing documentation for audits or regulatory reviews.

• Experience in designing or executing automated benchmark suites for LLMs or other GenAI systems is a plus.

• Familiarity with bias detection, harm classification, content safety tools, or policy evaluation frameworks is advantageous.

• Experience with use cases in regulated financial services is a plus.

• Experience influencing engineering standards or mentoring engineers in AI safety, Responsible AI, or production ML practices is a plus.

🏝️ Benefits

• Inclusive recruitment and professional development programs.

• Affinity groups that support underrepresented communities: ExperianPride, Ubuntu, Women in Experian, Aspire, and Connecting Generations.