IA Engineer

HarfangLab; Paris; Sur place; EUR 90 000 - 120 000; Plein temps

Avantages offerts par ce poste

Office in Paris

Health insurance

Meal vouchers

25 days leave

Résumé du poste

HarfangLab, a French cybersecurity scale-up in Paris, seeks an AI/ML engineer to help advance an AI-driven threat detection and investigation platform. You will contribute to prototype-to-production features, focusing on LLM-powered threat investigations, tool calling, and autonomous capability enhancements.

The role offers opportunities across machine learning, deep learning, and data engineering, with a strong emphasis on delivering real product value in a fast-growing security company.

Qualifications

• You can read and understand Python code.
• You have a solid understanding of how LLMs work: data gathering, prompting, fine-tuning, inference, attention, and tokenization.
• You have hands-on experience with LLMs via APIs or local deployments and have built applications such as RAG systems, tool-calling workflows, agents, or chatbots.

Responsabilités

• Build investigation agent pipelines (planning, tool calling, synthesis).
• Design and maintain an evaluation framework to measure system performance and track metrics.
• Evaluate foundation models (open-source and proprietary) and document trade-offs.
• Industrialize developments within a shared codebase through testing, packaging, and CI/CD.
• Integrate solutions into the product, deploy them, and monitor in production.

Outils

Python

LLM basics

LLM via APIs

RAG systems

Tool-calling

Agents

Chatbots

LangGraph

PydanticAI

Haystack AI

Scikit-learn

PyTorch

Description du poste

HarfangLab is a French scale-up specializing in cybersecurity that develops EDR (Endpoint Detection and Response), EPP (Endpoint Protection Platform ), and ASM (Attack Surface Management) solutions to detect and neutralize modern cyberattacks targeting an organization’s workstations and servers. Our engines, models, and algorithms identify abnormal behaviors and either generate security alerts or block program execution.

Since our creation in 2018, HarfangLab’s technology has received strong industry recognition, earning prestigious distinctions and becoming the first EDR to be certified by ANSSI in 2020, and later the first to obtain ANSSI qualification in 2025. We are also proud to have joined the French Tech 2030 program alongside 80 other innovative French companies, at a time when cyber resilience has become a major strategic priority for Europe.

We have raised a total of €30 million, enabling us to strengthen our teams, growing from 40 employees in 2023 to 130 today, and expand internationally across Europe.

Today, HarfangLab protects the endpoints of more than 800 clients of all sizes and across all sectors: CAC 40 industrial companies, government entities, SMEs, hospitals, and local authorities. With a strong collective spirit and international ambitions, HarfangLab continues its expansion while remaining true to its original mission: protecting organizations against increasingly complex cyber threats while enabling clients to retain full control over their data.

What you will do with us?

You will join the Artificial Intelligence team, a group of 7 people. This team has developed an initial system leveraging a Large Language Model to help cybersecurity analysts identify and respond to threats. The team is now working on enhancing this system with new capabilities, enabling it to perform advanced attack investigations autonomously.

You will contribute to the design, development, and deployment of these new features, from prototype to production. Your responsibilities will include:

• Building investigation agent pipelines (planning, tool calling, synthesis).
• Designing and maintaining an evaluation framework to measure system performance and track metrics over time.
• Evaluating foundation models (open-source and proprietary) against our use cases and documenting trade-offs between cost, latency, and quality.
• Industrializing developments within a shared codebase through testing, packaging, documentation, and CI/CD best practices.
• Integrating solutions into the product, deploying them, and monitoring them in production.

Depending on your interests and background, you may also have the opportunity to work on machine learning, deep learning, or data engineering projects.

About You

Hard Skills:

• You can read and understand Python code.
• You have a solid understanding of how LLMs work, including data gathering, prompting, fine-tuning, inference, attention mechanisms, and tokenization.
• You have hands‑on experience working with LLMs through APIs or local deployments and have built applications such as RAG systems, tool-calling workflows, agents, or chatbots.

Nice to have:

• Basic knowledge of cybersecurity.
• Experience with agent frameworks such as LangGraph, PydanticAI, Haystack AI, or similar.
• Knowledge of machine learning or deep learning frameworks such as Scikit‑learn, PyTorch, or equivalent.

Soft Skills:

• You are curious and autonomous, and you are comfortable taking ownership of topics that are not yet fully defined.
• You have strong analytical skills and can help structure complex problems so that other team members can contribute effectively.
• You enjoy collaborative work, communicate clearly, and are comfortable asking for or offering help when needed.
• You are motivated to actively contribute to integrating your work into the HarfangLab product.

What We Offer

Our Office and Team Culture

• Offices located in the heart of Paris, near Bourse (75002),
• High-performance equipment tailored to your needs and preferences (Mac/PC, additional screens),
• Thanks to our Office Manager, events regularly take place such as seminars, themed evenings, and more,
• An onboarding process to welcome each new colleague with an explanation of the roles within the different teams of the company and a mentor to guide you during your early days.
• Health, well-being & sport: Alan insurance + Alan Mind mental wellness app + Egym subscription, covered at 80% by HarfangLab,
• Meal vouchers: Swile card + access to an employee benefits platform.
• Paid time off: 25 days annual leave + 8-11 RTT days.
• Professional growth: Access to training programs and industry events tailored to your needs.