Research Scientist/Engineer (Agentic Systems)

White Circle
Paris, London
Workplace: HybridFull timeUSD 150,000 - 250,000 annuallyFunction: Data Science & Machine LearningSkills: ["Python","Containers","APIs","LLMs","Frontier models","Orchestration"]

Research scientist to build autonomous, large-scale environments that stress-test LLM agents (single and multi-agent) to failure, study breakdowns, and publish actionable insights. You will design adversarial, multi-agent environments, run end-to-end experiments, and turn findings into internal models and public writeups.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
White Circle
White Circle
2 months ago

Research Scientist/Engineer (Agentic Systems)

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 1 hour agoStatus: Live

Job Summary

Research scientist to build autonomous, large-scale environments that stress-test LLM agents (single and multi-agent) to failure, study breakdowns, and publish actionable insights. You will design adversarial, multi-agent environments, run end-to-end experiments, and turn findings into internal models and public writeups.
Location: Paris, London
Workplace: Hybrid
Employment Type: Full time
Job Function: Data Science & Machine Learning

Key Responsibilities

  • •Build adversarial environments for agents to probe failure modes and misalignment.
  • •Construct realistic multi-agent environments and instrument them so emergent breakdowns are observable.
  • •Run end-to-end experiments against external APIs and internal models, orchestrating many agents in parallel.
  • •Catalogue concrete agent failure modes and develop tooling to surface them at scale.
  • •Translate experimental findings into internal models of agent behavior and public writeups.

Pay and Benefits

Salary: USD 150,000 - 250,000 annually
Equity and Bonus:Equity
Perks:Health InsuranceRelocation

Key Requirements

  • •Experience building non-trivial agent environments or automated research pipelines that run end to end (single- or multi-agent) and can discuss what broke and why.
  • •Strong software and AI engineering skills; ability to independently orchestrate many agents and containers in parallel without the orchestration becoming a bottleneck.
  • •A track record of empirical research in agents, red-teaming, or post-training where you defined the question, ran it, and drew a defensible conclusion.
  • •Ability to define questions and run falsifiable experiments when there is no playbook, handling fuzzy concerns effectively.
  • •A background with frontier models and coding agents in daily work (AI power-user).
Experience:AI safetyAgentsReinforcement learningLarge language modelsMulti-agent systems
Skills:PythonContainersAPIsLLMsFrontier modelsOrchestration
Languages:English
Tech Stack:PythonDockerKubernetesLLMsAPIs

Company Brief

White Circle
Builds AI-driven products and services to help businesses automate workflows, extract insights from data, and improve decision-making using machine learning and natural language processing technologies.
Industry: AI & Machine Learning
Website