Join us to build safe and responsible AI systems focusing on LLM jailbreak detection, defense, and agentic AI safety. You will own high-impact projects from research to production, designing scalable safety infrastructure and red-teaming platforms.
Responsibilities
Advance AI Safety: Design, implement, and evaluate attack and defense strategies for LLM jailbreaks (prompt injection, obfuscation, narrative red teaming) and deploy them as production-grade services.
Build Scalable Safety Infrastructure: Architect and deploy distributed safety evaluation pipelines handling millions of requests, with real-time monitoring, alerting, and incident response.
Large-Scale Data Engineering: Design ETL pipelines for processing terabytes of safety-related data; build data lakes and feature stores.
Evaluate AI Behavior: Analyze human-AI interaction patterns to uncover behavioral vulnerabilities and tradeoffs.
Agentic AI Security: Build production workflows for multi-agent safety including self-checks and regulatory compliance.
MLOps & Model Deployment: Deploy safety models using containerized microservices, implement CI/CD, and manage model versioning.
Benchmark & Harden LLMs: Create automated evaluation protocols for safety and adversarial resilience.
Hirevector is a professional services and recruitment firm that provides an AI-powered technical interview intelligence platform. The company focuses on standardizing the hiring process through conversational, AI-driven assessments to ensure fairness, reduce bias, and improve candidate evaluation.
Master's degree in CS/EE/ML/Security or related field (Ph.D. preferred)
2+ years of industry experience in applied ML/AI research or ML engineering
Track record of publications in AI Safety, NLP robustness, or adversarial ML (ACL, NeurIPS, ICML, EMNLP, IEEE S&P, etc.) or equivalent applied research impact
Strong Python and PyTorch/JAX skills with experience deploying ML models to production
Demonstrated experience in LLM jailbreak attacks/defense, agentic AI safety, adversarial ML, or human-AI interaction vulnerabilities
Experience with containerization (Docker, Kubernetes) and cloud platforms (AWS, GCP, or Azure)
Proven ability to take research from concept to code to production deployment with rigorous testing and monitoring