AI role · Open offer

Développeur IA — RAG & Guardrails

CAT-AMANIA

This listing is optimized for AI-native talent: clear skills and tools so candidates know if they fit before they apply—and so you spend less time screening mismatches.

3 skills2 tools

Apply now Find matching talent

Share this role

At a glance

How you'll work, where, and key listing dates.

Employment: Freelance
Workplace: Hybrid
Location: 32 Avenue de Wagram, 75008 Paris, France · Hybrid
Compensation: EUR 500-650/day
Experience level: Senior
Team: RAG Security
Benefits & perks

About this role

What the team is looking for and how this position fits.

CAT-AMANIA is hiring a Senior Développeur IA — RAG & Guardrails on the RAG Security team (Hybrid · Paris, France). This is a hands-on role in LLM & generative AI—not a generic “AI enthusiast” post.

You will own LLM features, retrieval, agents, and evaluation end to end: problem framing, offline evaluation, safe rollout, and iteration from production signals. Success is measured with clear metrics (quality, latency, cost, or business KPIs)—not slide decks alone.

CAT-AMANIA ouvre une mission RAG + guardrails avec forte exigence de gouvernance et suivi opérationnel.

Le poste couvre retrieval, politiques de sécurité, tests de robustesse et monitoring continu.

Ce que vous allez faire

Livrer en production des systèmes RAG avec guardrails en production avec évaluation offline, monitoring et plan de rollback.
Travailler avec produit, métier et design pour cadrer les besoins et priorités.
Améliorer qualité des données, observabilité et KPI business liés aux usages IA.
Documenter runbooks, incidents et standards de sécurité pour l'équipe.

Profil recherché

Expérience concrète Python / stack ML-LLM avec features déjà déployées.
Bonne pratique SQL, expérimentation et communication claire aux non-tech.
Capacité à gérer les compromis qualité, coût, latence et sécurité.

Skills we're hiring for

What each capability means for this role—not a keyword checklist.

Python
Production Python for data pipelines, model code, APIs, and automated tests—not notebook-only workflows.
LangChain
Orchestrating LLM chains, tools, and retrieval with observable steps and failure handling.
NLP

Tools & stack

Platforms and products mentioned for this role (APIs, IDEs, vector DBs, CRMs, design tools, etc.).

Vector DBsTool
Embedding storage, hybrid search, and freshness strategies for RAG and semantic retrieval.
DockerTool
Containerized services and reproducible dev environments for ML and LLM workloads.

You're a strong fit if…

Tailored to this listing—use it as a self-check before you apply.

You can show evidence in your application: Montre une implémentation guardrails avec logs et policy tests.
Several of these show up in recent shipped work—not only on your CV: Python, LangChain, NLP, Vector DBs, and Docker.
You have owned LLM features, retrieval, agents, and evaluation in production: debugging live issues, running postmortems, and iterating from real user or business signals.
You are comfortable with the hybrid rhythm (Hybrid · Paris, France)—onsite collaboration when it matters, deep work when remote.
You explain trade-offs (quality, cost, latency, safety) in plain language—with numbers or examples, not buzzwords.

Apply

Candidate accounts only: add your headline and bio on , and optionally a CV link or PDF so recruiters see your full résumé. Then write a short pitch below—applications use your login email.

What the employer asked for

Montre une implémentation guardrails avec logs et policy tests.

Register, add a headline and bio, then you can attach a CV link or PDF on My account before you apply. That keeps applications tied to your profile and makes it easier for employers to review your background.

Suggested

AI talent you may also like

Profiles ranked by overlap with this role's skills and tools—handy if you're hiring for a team or comparing backup candidates.

Elena Varga

Forward Deployed AI Engineer

Full-time · €95k–115k + equity · Amsterdam, NL

Profile active · Apr 5

4 skills · 2 projects · 2 roles · 3 use cases

Built

Regulated RAG rollout
Multi-tenant pipeline: chunking, ACL-aware retrieval, audit logs, and human approval for outbou…
Demo Repo Link
Eval harness
Golden sets + LLM-as-judge with calibration against human labels; CI gate before prod prompt ch…
Repo

Top skills

Python

Similar open roles

Other listings that share skills or tools with this one—useful if you want comparable stacks or backup options.

Développeur IA — RAG & Guardrails

AI talent you may also like

Elena Varga

Similar open roles

Omar El-Sayed

David Cohen

James Okoro

Yuki Tanaka

Développeur IA Générative / Generative AI Engineer

Développeur IA / RAG / Python

AI Engineer / Développeur IA Full Stack — Freelance

Senior LLM Engineer — enterprise RAG

LLM Engineer — answer engine