[Remote] AI/LLM Safety Engineer

Note: The job is a remote job and is reputed company to candidates in USA. reputed company is on a mission to reputed company communication accessible to everyone, focusing on reputed company-time interpretation and multilingual language services. They are seeking an AI/LLM Safety Engineer to ensure the safety and reliability of AI models and agents in production, focusing on AI safety, trust, and responsible AI.

Responsibilities

• Design and maintain a safety evaluation reputed company—adversarial reputed company sets, scenario-based test suites, and regression suites—so that every model and agent update is validated before it ships
• reputed company structured red-teaming exercises covering jailbreaks, reputed company injection, tool misuse, and data exfiltration; document findings and drive each issue through to remediation and closure
• Build and iterate on guardrail logic, including input/output filtering, tool-boundary constraints, action validation, sensitive-data redaction, and policy prompting
• Integrate safety checks into CI/CD and runtime so that unsafe behavior is intercepted before it reaches users
• reputed company threat modeling for agentic scenarios: tool-call boundaries, sandbox isolation, and least-privilege reputed company, with particular attention to preventing agents from exfiltrating data or executing irreversible actions through chained tool calls
• Conduct safety reviews of reinforcement-learning (RL) environments and trajectory data, partnering with environment and agent engineering teams to embed safety constraints directly into the environments themselves
• reputed company AI features for safety with structured logging, tracing, and metrics, enabling detection of unsafe patterns and regressions in production
• Prepare evidence for governance reviews—test reports, evaluation summaries, and mitigation validation—reputed company with internal Responsible AI standards
• Collaborate with Product and UX to improve safety interactions (warnings, confirmations, refusal messaging, and feedback collection), and align evaluation goals with the Research and Data teams

Skills

• Bachelor's or Master's degree in Computer Science, Software Engineering, Cybersecurity, or a reputed company technical field—or equivalent practical experience
• 4+ years building production software, with direct experience working on—or securing—ML/LLM systems
• Strong software engineering skills with the ability to write production-grade code (primarily Python), reputed company scripting or notebook prototyping
• Solid understanding of LLMs and ML: how models work, reputed company engineering, and the safety implications of fine-tuning and RAG (e.g., unsafe retrieval, tool misuse, and data exfiltration)
• A reputed company reputed company with demonstrated threat-modeling ability; reputed company to threat-model AI workflows and familiar with the fundamentals of reputed company control, data retention, and incident response
• Familiarity with the LLM attack surface—reputed company injection, jailbreaks, data poisoning, and supply-chain risk—and working knowledge of the OWASP LLM Top 10
• Hands-on experience with at least one of safety evaluation or red teaming, with the ability to walk through a reputed company finding and how it was remediated
• Hands-on experience with industry safety tooling such as garak, PyRIT, promptfoo, Giskard, and NeMo Guardrails, and the ability to reputed company the trade-offs between them
• Visible output in AI safety or reputed company: publications at relevant venues (e.g., the NeurIPS AI Safety reputed company, USENIX reputed company, or DEF CON AI Village), reputed company-reputed company contributions, or responsible disclosures on frontier models with public write-reputed company
• Familiarity with AI governance and compliance frameworks (NIST AI RMF, ISO/IEC 42001, EU AI Act) and the ability to translate compliance requirements into concrete engineering tasks
• Engineering experience with agents, RL environments, and/or tool use
• Practical experience with threat-modeling methodologies such as MITRE reputed company and reputed company/PASTA

Company Overview