Senior ML Engineer – AI Safety

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

📋 Description

• Take the lead in designing and executing 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 for jailbreak and prompt injection, and automated safety benchmarks.

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

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

• Oversee incident response and root cause analysis for AI-related safety concerns, including conducting post-incident reviews and developing remediation playbooks.

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

• Provide mentorship to junior and mid-level engineers.

• Represent 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.

• Proficient in Python programming.

• Familiarity with machine learning frameworks like TensorFlow, PyTorch, scikit-learn, or similar tools.

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

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

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

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

• Excellent proficiency in both written and verbal English.

• Experience in designing or managing automated benchmark suites for LLMs or other GenAI systems.

• Knowledge of bias detection, harm classification, content safety tools, or policy evaluation frameworks.

• Experience in regulated financial services contexts, such as fraud detection, credit risk, customer service automation, or model risk management.

• Proven ability to influence engineering standards or mentor engineers in AI safety, Responsible AI, or production ML practices.

🏝️ Benefits

• Flexible remote work arrangement.

• Commitment to inclusive recruitment and professional development initiatives.

• Access to affinity groups: ExperianPride, Ubuntu, Women in Experian, Aspire, and Connecting Generations.