S Senior AI Engineer - Freelance Paris, France ( Non précisé ) Freelance · Senior il y a 2 sem. ›

Zeroday Cyber Academy; Paris; Híbrido; EUR 96.000 - 152.000; Tempo parcial

Resumo da vaga

Mirakl recherche un(e) Senior AI Engineer pour concevoir, construire et faire évoluer des systèmes d'IA en production, au croisement du génie logiciel et du ML. Vous travaillerez sur des architectures agentiques, RAG et chaînes d'outils, en collaboration avec les équipes produit et ingénierie.

Poste basé à Paris ou Bordeaux avec une journée de télétravail par semaine; opportunité de contribuer à des produits SaaS avancés et à la stratégie IA de Mirakl.

Qualificações

• 5+ années d'expérience en génie logiciel / IA appliquée.

Responsabilidades

• Concevoir, construire et déployer des systèmes d'IA en production.
• Intégrer les systèmes d'IA dans les plateformes et applications internes.
• Itérer pour générer un impact mesurable sur les activités.
• Assurer la qualité, la sécurité et la fiabilité des systèmes.
• Favoriser l'adoption et l'extension des capacités IA dans l'entreprise.

Conhecimentos

Python

SQL

IA engineering

Software engineering

Ferramentas

OpenAI

Anthropic

Gemini

Mistral

LangGraph

LangChain

LlamaIndex

Vector databases

Docker

Kubernetes

AWS

GCP

Descrição da vaga

About Mirakl

Founded in 2012, member of French Tech Next40, Mirakl provides a SaaS marketplace operating system (enterprise marketplaces, AI-powered multichannel selling, retail media, agentic commerce). 750+ employees in 9 offices (Paris, Barcelona, Bordeaux, Boston, London, Munich, New York, Sydney, Tokyo), including 350+ tech team members mainly based in France. Its ecosystem runs 450+ B2C and B2B marketplaces, with brands like Macy's, Decathlon, Carrefour, Asos and Airbus Helicopters.

About the job

Design, build, and scale production-grade AI systems that power the next generation of intelligent commerce. You will work at the intersection of Software Engineering, Machine Learning, and Generative AI to build AI-native products, agentic systems, and platform capabilities used by Mirakl customers and internal teams.

This is a freelance position based in Paris or Bordeaux, with 1 day of remote work per week.

Why now

Generative AI and AI Agents are fundamentally reshaping commerce software and the way teams work. At Mirakl, AI is becoming a core part of the product strategy, from Catalog Transformer and content generation to AI Agents and Agentic Commerce. We are looking for a Senior AI Engineer to transform the way internal teams work, and to have a significant impact on the agentic side of our SaaS products. You won't be joining a company that's thinking about AI. You'll be joining one that's already building it.

1. Design & build AI systems

• Design, build, and deploy production-grade AI systems for Mirakl internal operations.
• Develop solutions leveraging LLMs, RAG, AI Agents, Multimodal AI and evaluation frameworks.
• Architect complex agentic workflows including tools, memory, retrieval, planning, and guardrails.
• Rapidly prototype new capabilities and evolve them into scalable, reliable AI production systems.

2. Integrate across the stack

• Connect AI systems to internal platforms, business applications, and data sources across the company.
• Enable AI agents to interact with systems such as CRM, data platform, Drive, Jira, support tools, and internal knowledge bases.
• Design robust orchestration layers between models, APIs, tools, retrieval systems, and business workflows.
• Ensure reliability, observability, scalability, and maintainability across the entire AI stack.

3. Iterate for impact

• Partner with end users, business teams, Product Managers, and Engineers to identify high-value opportunities for AI.
• Run pilots and experiments, gather qualitative and quantitative feedback, and measure business impact.
• Analyze usage patterns, failure modes, costs, latency, and performance metrics.
• Continuously improve accuracy, reliability, adoption, and user experience through data-driven iteration.

4. Ensure quality, security & reliability

• Implement evaluation frameworks, guardrails, validation layers, and monitoring systems.
• Design AI systems that are secure, explainable, and production-ready.
• Ensure compliance with data security, governance, and access control requirements.
• Document architectures, capabilities, limitations, KPIs, and operational best practices.

5. Drive adoption & enablement

• Build a scalable ecosystem of AI systems and agents that empower both internal teams and customers.
• Support teams in adopting AI-powered workflows and integrating AI into their daily operations.
• Contribute to AI engineering standards, reusable frameworks, and best practices across the company.
• Act as a champion for AI-driven ways of working and help shape Mirakl's transition toward Agentic Commerce.

Stack and tools

• Languages : Python and SQL
• AI stack : OpenAI, Anthropic, Gemini, Mistral and open-source models
• Agentic & retrieval : LangGraph, LangChain, LlamaIndex, MCP and vector databases
• Infrastructure : AWS or GCP, Docker and Kubernetes

What makes you successful

• Strong engineering mindset: able to design reliable and scalable systems
• Strong AI expertise: able to translate the latest AI capabilities into production products
• Strong product mindset: able to balance technical excellence with business impact
• Focus on measurable outcomes, not technical complexity

You’ll love this job if you have:

• 5+ years of experience in Software Engineering, ML Engineering, Applied AI, or related fields
• Strong Python and software engineering fundamentals

Ce qui te ferait sortir du lot (côté sécurité)

Zeroday : sur un poste comme celui-ci, ce qui fait la différence côté sécurité :

• traiter les garde-fous des agents comment du code : limiter les outils exposés, filtrer les sorties, borner les actions possibles avant de brancher un agent sur un CRM ou un Jira ;
• contrôler le périmètre de données qui alimente le RAG par utilisateur, sinon l'agent restitue à l'un ce que l'autre seul avait le droit de lire ;
• ne rien coller de sensible dans les prompts : une requête envoyée à un modèle hébergé chez un tiers quitte l'entreprise, secrets et données clients compris ;
• garder un jeu d'évaluation de non-régression avant tout changement de modèle ou de prompt : sans lui, une régression passe en production sans se signaler.