---
title: 'Research Engineer (Evals) at White Circle'
canonical: 'https://feeny.ai/job/research-engineer-evals-white-circle-paris-0r42jk316m7n'
type: 'job'
last_seen: '2026-09-05'
---

# Research Engineer (Evals) at White Circle

- **Company:** White Circle
- **Location:** Paris, France
- **Compensation:** $150k–$250k
- **Employment:** full-time
- **Work type:** hybrid
- **Posted:** 2026-06-28
- **Last confirmed live:** 2026-09-05
- **Apply:** https://jobs.ashbyhq.com/whitecircle/07d24ec8-117f-4849-8dd5-2c2bc2cfbb40/application

**Skills:** Python, LLM benchmarking, Synthetic data generation, LLM inference setup, Parallel call orchestration, Rate-limit handling, Automated red-teaming, Reward models, Monitoring, Safety benchmarks, Published papers in evals/safety-evaluation

> Build and maintain internal benchmark suites for AI safety, including single/multi-turn content and agentic guardrails. Collaborate with the product team to evaluate flagship models and research agent behaviors in the wild.

## Job description

TLDR: We're looking for a research engineer to build and maintain our internal suite of benchmarks, covering single/multi-turn content and agentic guardrails. The research engineer would also work with the team on projects studying agent behaviours in the wild.

## About us

White Circle https://whitecircle.ai/ 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 in the real world: where agents break, how misalignment actually looks like to the end user, and how it is present in the model internals. We build the evals, benchmarks, environments, and tooling that empirically study high-impact agent reliability concerns — some of which become the guardrails shipped in our products, and some of which become public writeups.

You will:

- Own and maintain our internal benchmark suite, covering single/multi-turn content guardrails and agentic safety.
- Build benchmarks that distinguish specific model capabilities.
- Work with the product team to build evals covering core functionality of our flagship models.
- Build benchmarks for new features coming out of the research team.
- Adapt and extend evals to new verticals and changing product data.
- Work on research projects that study and quantify realistic agentic and LLM failure modes in the wild.

You’ll fit right in if you:

- Have built an LLM benchmark from scratch that distinguished specific model capabilities (i.e., produced a measurable, defensible capability difference, not just a score).
- Have built synthetic data for post-training textual or multimodal models.
- Can reproduce a published benchmark result and identify where the original methodology is fragile or misleading.
- You write Python that other people can build on. Our whole stack is Python; we want someone who has shipped and maintained production code and who factors messy problems into clean abstractions others can extend.
- You can write efficient LLM inference setups, including sensible orchestration of parallel calls, retries, rate-limit handling.
- An AI power-user — fluent with frontier models and coding agents day to day.

A big plus:

- Automated red-teaming experience
- Have worked across a range of agentic scaffolds and reproduced public benchmark results on them
- Strong knowledge of existing reward-model / monitoring / safety benchmarks
- One or more published papers in the evals / safety-evaluation space

## 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 private medical insurance for London-based roles for now).
- 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

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

Please submit your application in English.

## About White Circle

## Company Overview
- **One-liner**: White Circle is a control layer for AI in production, providing safety, security, evals, and performance optimization through a unified API.
- **Entity Type**: Private (Seed stage)
- **Headquarters**: Dover, Delaware, United States (operational hub in Paris, France)
- **Founded**: 2025
- **Founders**: Denis Shilov (Founder & CEO)

## Core Business
- **Primary industry**: AI Governance, AI Security, AI Observability
- **Target customers**: B2B, Enterprise (companies deploying AI agents, chatbots, or LLM-powered applications)
- **Mission or purpose**: To give organisations visibility into how their AI behaves, help them respond when things go wrong, and provide a unified system for improving reliability, safety and compliance.

## Products & Services
- **White Circle Platform**: A single API that integrates three layers:
  - **Protect**: Custom low-latency guardrails for blocking unsafe inputs, preventing jailbreaks, detecting prompt injections, PII leakage, and sensitive data leaks.
  - **Observe**: Real-time analytics including topic classification, user behavior clustering, custom metrics, error rate analysis, sentiment analysis, and risk scoring.
  - **Improve**: Model routing, dynamic prompt engineering, context enrichment, and automated optimization based on labelled user feedback.
- **CircleGuardBench**: A proprietary benchmark for evaluating AI moderation models across harm detection, jailbreak resistance, false positives, and latency.
- **KillBench**: A benchmark of hidden LLM biases in critical decisions (life-and-death scenarios).

## Market Standing
- **Valuation/Market Cap**: Not disclosed
- **Key Metric**: $11M raised in seed funding (announced May 2026)
- **Notable Investors/Partners**: Backed by prominent AI and technology leaders including Romain Huet (ex-Head of Product @DeepMind), Dirk Kingma (Anthropic), Guillaume Lample (Mistral), Thomas Wolf (Hugging Face), Olivier Pomel (Datadog), François Chollet (Keras), Mehdi Ghissassi (ex-DeepMind), Paige Bailey (DeepMind), and David Cramer (Sentry).
- **Growth Signals**:
  - 21 employees (+283.3% YoY, +9.5% monthly growth)
  - Monthly website traffic: 32,090 visits (+682.7% yearly)
  - Active job postings: 6 (monthly job posting growth +20%)
  - SOC 2 Type II and HIPAA compliant
  - Operates in 7 countries (France, Russia, Netherlands, Serbia, Switzerland, Georgia, Spain)

## Competitive Advantages
- **Proprietary self-adjusting models** optimized for low-latency and high performance
- **Unified platform** that combines safety, security, evaluation, and performance optimization – no need for multiple point solutions
- **Enterprise-grade compliance** (SOC 2 Type II & HIPAA)
- **Strong network effects** from backing by leaders at OpenAI, Anthropic, DeepMind, Hugging Face, and Datadog
- **Automated red-teaming** and continuous improvement through user feedback

## Strategic Focus
- Accelerate product development and expand the team across the US, UK, and Europe
- Grow global customer base across healthcare, finance, hiring, and security verticals
- Continue building benchmarks (CircleGuardBench, KillBench) to shape AI safety standards
- Maintain deep integration with the AI open-source ecosystem

## Why Work Here
- **Culture**: “Smart, friendly, and fun” team with a strong engineering and research focus (43% technical staff)
- **Location**: Based in Paris, France with a hybrid work model (office + remote)
- **Benefits**:
  - Strong salary
  - 20 paid days off (plus ability to take more for recovery)
  - Free education (company covers learning costs)
  - Team offsites several times a year
- **Open roles** (June 2026): QA Engineer, Product Engineer (Backend), DevOps Engineer, Product Designer, AI Engineer (Audio), Data Engineer
- **Impact**: Build the future of AI safety at a well-funded, high-growth startup with world-class investors

## Sources
1. [whitecircle.ai](https://whitecircle.ai)
2. [whitecircle.ai/careers](https://whitecircle.ai/careers)
3. [LinkedIn – White Circle](https://www.linkedin.com/company/whitecircle)
4. [Tech.eu – White Circle lands $11M](https://tech.eu/2026/05/12/white-circle-lands-11m-to-help-companies-secure-ai-systems/)

## Other roles at White Circle

- [Finance Lead](https://feeny.ai/job/finance-lead-white-circle-us-san-francisco-or-s3jtsbzkwt7f) — US San Francisco OR, NY
- [Product Brand Designer](https://feeny.ai/job/product-brand-designer-white-circle-us-san-francisco-or-3v7jkx8gskhf) — US San Francisco OR, NY
- [Founding Account Executive](https://feeny.ai/job/founding-account-executive-white-circle-us-san-francisco-or-rns9xb4d5gj6) — US San Francisco OR, NY
- [Recruiter (Research)](https://feeny.ai/job/recruiter-research-white-circle-remote-1vekq2rdfrvz)
- [DevOps Engineer](https://feeny.ai/job/devops-engineer-white-circle-paris-y84p4fve5nn1) — Paris, France
- [Founding Events Lead](https://feeny.ai/job/founding-events-lead-white-circle-new-york-wczngn43ffxc) — New York, NY
- [Partnerships Manager](https://feeny.ai/job/partnerships-manager-white-circle-london-c3ep31m67xse) — • London, United Kingdom
- [Senior Data Labeler](https://feeny.ai/job/senior-data-labeler-white-circle-paris-vtp78vea9yp4) — Paris, France
- [AI Red Team Engineer](https://feeny.ai/job/ai-red-team-engineer-white-circle-j1xbb74qxv2e) — •, United States
- [ML Infrastructure Engineer](https://feeny.ai/job/ml-infrastructure-engineer-white-circle-paris-cjvfwvec3k00) — Paris, France