Research Scientist - Agentic Systems & AI Safety

whitecircle

France

Hybride

EUR 90 000 - 130 000

Plein temps

14 jours+

Une candidature complète en une minute

Un CV et une lettre de motivation personnalisés, prêts à envoyer.

Passez les filtres ATS

Avantages offerts par ce poste

Paid time off
Hybrid Paris relocation package
Comprehensive medical insurance (FR)
All hardware and tools provided
Subscriptions for AI agents and IDEs
Team off-sites twice a year

Résumé du poste

White Circle, an AI Safety company, seeks a research scientist to build adversarial, large-scale environments for LLM agents (single and multi-agent) to push them to failure. You will run experiments, catalogue failure modes, and publish findings to advance AI safety.

The role emphasizes strong software and AI engineering, end-to-end experimentation, and driving empirical, falsifiable insights into agent behaviour.

Qualifications

  • Experience building non-trivial agent environments or end-to-end research pipelines.
  • Strong software and AI engineering skills with multi-agent orchestration.
  • Track record of empirical research in agents, red-teaming, or post-training.

Responsabilités

  • Build adversarial and multi-agent environments to study failures.
  • Run end-to-end experiments against external APIs and internal models.
  • Catalogue agent failure modes and surface them at scale.
  • Turn findings into internal models of behaviour and public writeups.

Connaissances

Agent environments
Empirical research
AI engineering
Experiment design
Frontier models
Orchestration of agents

Outils

Python
Docker
APIs

Description du poste

White Circle, an AI Safety company, seeks a research scientist to build adversarial, large-scale environments for LLM agents (single and multi-agent) to push them to failure. You will run experiments, catalogue failure modes, and publish findings to advance AI safety.

The role emphasizes strong software and AI engineering, end-to-end experimentation, and driving empirical, falsifiable insights into agent behaviour.

Obtenez votre examen gratuit et confidentiel de votre CV.

ou faites glisser et déposez votre fichier ici.

Similar jobs

Postes similaires à comparer

Research Scientist/Engineer (Agentic Systems)
Research Scientist/Engineer (Agentic Systems)

whitecircle • France

Hybride
EUR 90 000 - 130 000
Paid time off
Hybrid Paris relocation package
Comprehensive medical insurance (FR)
+3
Senior Research Scientist Agentic AI Systems
Senior Research Scientist Agentic AI Systems

European Tech Recruit • Paris

Sur place
EUR 60 000 - 90 000
Senior AI Data Engineer: Agentic Systems & LLM Ops
Senior AI Data Engineer: Agentic Systems & LLM Ops

mLabs • France

À distance
EUR 116 000 - 133 000
Equity
Growth opportunities
Impact
+1
AI Safety Benchmark Engineer — Hybrid (Relocation)
AI Safety Benchmark Engineer — Hybrid (Relocation)

whitecircle • France

Hybride
EUR 70 000 - 95 000
Research Engineer (Evals)
Research Engineer (Evals)

whitecircle • France

Hybride
EUR 70 000 - 95 000
Staff Engineer, Safety for AI Agents
Staff Engineer, Safety for AI Agents

Cohere • Paris

Hybride
EUR 60 000 - 90 000
Inclusive work culture
Cutting-edge AI research team
Weekly lunch stipend
+5
AI Alignment & Safety Research Scientist
AI Alignment & Safety Research Scientist

Lexsi Labs • Paris

Sur place
EUR 60 000 - 90 000
Remote AI Safety Red Teamer: Stress-Test Frontier Models
Remote AI Safety Red Teamer: Stress-Test Frontier Models

Mercor • Paris

À distance
EUR 83 000 - 100 000
AI Research Scientist (Paris)
AI Research Scientist (Paris)

Lexsi Labs • Paris

Sur place
EUR 60 000 - 90 000
AI Cybersecurity Research Engineer - RL & Defense Systems
AI Cybersecurity Research Engineer - RL & Defense Systems

Cyber StrategiX • Paris

À distance
EUR 82 000 - 118 000