Senior AI Engineer, AI Safety
United States · anteayer
Construirás y desplegarás bucles de automatización agentica basados en LLM para evaluación de seguridad, red-teaming y pruebas de modelos, y entrenarás sistemas para detección de contenido dañino y guardrails en tiempo de ejecución. También convertirás ideas de investigación en seguridad de IA en soluciones de producción escalables.
- Modalidad
- Remoto
- Nivel
- Senior
- Experiencia
- 8+ años
Skills
Sobre el puesto
## Responsibilities • Compose, build, and deploy foundational agentic automation loops for safety evaluations, red-teaming, model testing, model post-training, and ablations • Train and implement specialized systems for harmful-content identification, content quality coordination, and run-time guard-railing • Build and guide automated research frameworks using LLMs and autonomous agents to discover vulnerabilities • Generate or augment safety datasets for benchmarking or training and propose novel alignment techniques • Engineer proof-of-concept safety interventions and research ideas into robust, scalable production solutions • Partner with researchers, platform engineers, and data scientists to connect AI safety research with practical automated systems ## Requirements • Bachelor’s degree or Master’s degree with equivalent experience in Computer Science, Machine Learning, Software Engineering, or a related field • 8+ years of experience in ML engineering or software engineering • Proven experience building complex, automated workflows using LLMs, including multi-turn tool-calling, orchestration, and autonomous agent loops • Deep proficiency in one or more languages such as Rust or Python • Experience with machine learning frameworks like PyTorch • Ability to tackle open-ended, ambiguous problems and experiment, fail, iterate, and pursue solutions • Ability to own a project from initial white-boarding of a research idea to final deployment of a scalable production system • Prior domain experience in Trust & Safety, cybersecurity, threat intelligence, adversarial machine learning, or content moderation • Hands-on experience developing, fine-tuning, or deploying models for harm detection, content safety filtering, or run-time AI guardrails • Contributions to projects using LLMs to automate coding, data synthesis, or scientific research tasks • Active contributions to publicly available agent frameworks or AI safety benchmarking tools ## Benefits • Equity • Comprehensive benefits package • Competitive salary
Publicada el 7 nov 2026
