Research Scientist/Engineer (Agentic Systems)

WhitecircleParis, FrancePosted 2h agoonsite

TLDR: We're looking for a research scientist to build autonomous, large-scale environments that push LLM agents (single and multi-agent) to failure, and study how they actually break.

About us

White Circle is an AI Safety company building the safety, reliability, and optimization layer for AI systems. At the core of our platform are policies – simple natural-language rules that define what an AI model should and shouldn’t do. We automatically test, enforce, and continuously improve these policies at scale.

We’ve raised $11M from top funds, founders, and senior leaders at OpenAI, Anthropic, HuggingFace, Mistral, DeepMind, Datadog, Sentry, and others
We process over 100M+ API calls every month
We fine-tune and train our own LLMs so they run faster and cheaper than any open or proprietary model

We’re a small, highly focused team. If you want to work deeply on hard problems, see your work ship to production quickly, and influence how AI safety is actually built – you’re the one we need.

About the team

White Circle's fundamental research team works on the science of how AI systems fail: where agents break, why misalignment and unsafe behaviours emerge, and how to catch them before they reach the real world. We build the evals, benchmarks, environments, and tooling that empirically study the most pressing AI safety concerns — some of which become the guardrails shipped in our products, and some of which become public writeups.

You will

Build adversarial environments for agents: complex, uncertain settings that sit on the boundary of agent capability and alignment, where failure is informative rather than trivial.
Build realistic multi-agent environments and instrument them so emergent breakdowns are observable — failures that arise from the agents themselves, not ones scripted from the outside.
Run experiments end to end, against external APIs and our own models, orchestrating many agents in parallel.
Catalogue concrete agent failure modes and build the tooling to surface them at scale.
Turn findings into internal models of agent behaviour and into public writeups.

You’ll fit right in if you:

Have built at least one non-trivial agent environment or automated research pipeline that ran end to end (single- or multi-agent), and can talk through what broke and why.
Strong software and AI engineering. Can independently orchestrate many agents and containers in parallel without that orchestration being the 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.
A fast empirical iterator who is comfortable defining the question when there's no playbook: can take a fuzzy concern ("do these agents collude under pressure?") and turn it into a concrete, falsifiable experiment.
An AI power-user — fluent with frontier models and coding agents in your daily work.

A big plus:

Published research at A* venues on automated red-teaming, agentic environments, or post-training.
Experience building monitoring for model failures and anomalous behaviour.
Experience reproducing public benchmark results and finding where the original methodology is fragile or misleading.
An MSc or PhD in machine learning, computer science, cognitive science, computational neuroscience, physics, or a related quantitative field.
AI safety fellowship (MATS, ASTRA, Anthropic Fellows, etc.), or a comparable self-directed research record.

Why White Circle

Paid time off in line with your local regulations, no matter where you work from
Work from Paris (hybrid) with a relocation package available, or work from London (note: we are unable to provide relocation support or medical insurance for London-based roles)
Meaningful equity package
Comprehensive medical insurance for our France-based team
All the hardware, tools, and services you need
Covered subscriptions for AI agents and IDEs
Team off-sites twice a year: we’ve recently been to the Alps and to Saint-Tropez

How we hire

Introductory call with HR (25 min)
Take-home test task
Technical interview with Head of Fundamental Research (60 min)
Final conversation with our CEO (45 min)

Please submit your application in English.

Find Jobs in France on Arbeitnow

Skills

Research

Similar roles

Product Manager - Device Data Management (Fluent French & English)
Kaluza·Paris, France
Job title: Product Manager - Device Data Management (Fluent French & English)  Location: Paris — Hybrid (3 days in office) Salary: €57,600 - €72,000 Team: Product Management - Data Device Management  Reporting to: Group Product Manager This role is based in Paris, France and requires the successful candidate to be based in or willing to relocate to Paris. Fluent French and English (spoken and…
- On-site
- Full-time
2h ago
Senior Software Engineer I
Kaluza·Paris, France
Job Title: Senior Engineer I Location: Paris (Hybrid) Salary: €54,000 - €70,000 Team: Client Engineering  Reporting To: Software Engineering Manager This role is based in Paris and requires an existing right to work in France. At this time, we are not able to offer visa sponsorship for this role. We are committed to building a diverse, global team and our…
- On-site
- Full-time
2h ago
Product Manager - Energy Billing (Fluent French & English)
Kaluza·Paris, France
Job title: Product Manager (Billing) Location: Paris — Hybrid (3 days in office) Salary: €57,600 - €72,000 Team: Product Management - Billing & Payments Reporting to: Head of Product This role is based in Paris, France and requires the successful candidate to be based in or willing to relocate to Paris. Fluent French and English (spoken and written) are essential for this position.  At…
- On-site
- Full-time
2h ago
Product Manager (Data) - Fluent French & English
Kaluza·Paris, France
Job Title: Product Manager (Data) Location: London, Bristol or Paris (Hybrid - 3 days in office) Team: Data Products Reporting To: Director of Product This role is based in London, Bristol or Paris and requires existing right to work in the UK or France. At this time, we are not able to offer visa sponsorship for this role. We are committed to building…
- On-site
- Full-time
2h ago
Product Manager (CCaaS) - French Speaking
Kaluza·Paris, France
Job title: Product Manager  Location: Paris — Hybrid - 3 days in office Salary: €45,600 - €57,000 Team: Product Management - Customer Care Value Stream Reporting to: Head of Product  This role is based in France and requires the successful candidate to be based in or willing to relocate to France. Fluent French and English (spoken and written) are essential for this position.  At…
- On-site
- Full-time
2h ago
Enterprise Account Executive - France
Verkada·Paris, France
<div class="content-intro"><h3>Who We Are</h3> Verkada is transforming how organizations protect their people and places with an integrated, privacy-sensitive AI-powered platform that includes solutions for video security, access control, air quality sensors, alarms, intercoms, and visitor management.  We’ve got serious momentum in the market: more than 30,000 customers (including 100+ of the Fortune 500), <a href="https://www.cnbc.com/2025/12/03/verkada-capitalg-valuation-security.html">a $5.8B valuation</a>, more than $1…
- On-site
- Full-time
2h ago
Director, Enterprise Sales
Yext·Paris, France
<div class="content-intro">Yext (NYSE: YEXT) is the enterprise agentic marketing platform. Built on the world's most comprehensive structured data platform for local businesses, Yext gives brands and their partners the visibility intelligence to win every moment of discovery – across AI and traditional search. Yext's API-first architecture connects structured data to APIs, MCP servers, and generative interfaces, so partners and developers…
- On-site
- Full-time
2h ago
Account Executive - Mid-Market - France
Primer.io·France
An Introduction to Primer Primer is the unified infrastructure for global payments. We give finance and payments teams the visibility and control to reduce complexity, improve performance, and capture more revenue - all from a single platform. Backed by Sofina, Peak XV Partners, ICONIQ, Tencent, Accel, and Balderton, we're building the payments layer the world's best companies rely on. Watch…
- On-site
- Full-time
2h ago