Aller au contenu principal
Staff LLM Engineer — Agents & tool use | Mistral AI | Berli… · Ganloss
Staff LLM Engineer — Agents & tool use
Focus: Generative AI
Paris · 50-200 employees · Startup · GenAI: Yes
Cette annonce est pensée pour les profils IA : compétences et outils clairs pour savoir si le poste correspond avant de postuler — et pour réduire les mauvais matchs au screening.
4 compétences 2 outils
Partager ce poste
Copier le lien
Lieu de travail Hybrid
Localisation Berlin, Germany · Hybrid
Rémunération €120k–€145k Équipe Avantages Relocation support, conference budget, sabbatical policy. Comment postuler Link a repo or design doc for an agent with human-in-the-loop.
Publiée le 7 mai 2026
Mise à jour 3 juil. 2026 Mistral AI is hiring a Staff Staff LLM Engineer — Agents & tool use on the Applied research → prod team (Hybrid · Berlin, Germany). 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.
Our applied team ships agentic assistants for operations teams across the DACH region. We need a Staff engineer who can own architecture for multi-step workflows, safety layers, and multilingual rollouts.
Berlin hybrid; you will collaborate with research, infra, and compliance from day one.
What you will do
Design planning, retrieval, and execution graphs with explicit human-approval gates. Lead postmortems for tool failures, prompt regressions, or data leakage near-misses. Establish engineering standards: tracing, structured logging, redaction, and secret hygiene. Coach senior ICs; review designs for cost, latency, and maintainability. Represent engineering in customer security reviews for agent features. What we look for
8+ years production software with 3+ on LLM/agent systems at scale. Expert Python; deep knowledge of vector DBs, OpenAI-compatible APIs, orchestration frameworks. Written communication that scales across time zones (EN + DE professional fluency ideal). Evidence of cross-functional leadership without people-management requirement. Nice to have
Experience with regulated workloads (finance, healthcare adjacent). Contributions to OSS agent frameworks or retrieval papers. 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.
OpenAI API
Calling frontier APIs with retries, cost controls, prompt versioning, and safety filters.
Vector DBs
Embedding storage, hybrid search, and freshness strategies for RAG and semantic retrieval.
Docker Tool
Containerized services and reproducible dev environments for ML and LLM workloads.
AWS Tool
Regular use of AWS in the LLM & generative AI stack—configuration, debugging, and team conventions.
✓ You can show evidence in your application: Link a repo or design doc for an agent with human-in-the-loop. ✓ Several of these show up in recent shipped work—not only on your CV: Python, LangChain, OpenAI API, Vector DBs, and Docker. ✓ You have led LLM & generative AI initiatives across teams—setting technical direction, review standards, and rollout plans others could follow. ✓ You are comfortable with the hybrid rhythm (Hybrid · Berlin, Germany)—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. ✓ You read the full listing (comp: €120k–€145k, benefits in At a glance) and your expectations align. Ce que l’employeur demande
Link a repo or design doc for an agent with human-in-the-loop.
Connectez-vous avec un compte candidat pour postuler
Inscrivez-vous, ajoutez une accroche et une bio, puis vous pourrez joindre un lien ou un PDF de CV dans Mon compte avant de postuler. Vos candidatures restent liées à votre profil et les employeurs voient plus facilement votre parcours.
Suggestions
Profils IA qui pourraient vous intéresser Profils classés par recoupement avec les compétences et outils de ce poste — utile si vous recrutez une équipe ou comparez des profils.
Offres similaires D’autres annonces partageant compétences ou outils — utile pour des stacks comparables ou des options de repli.
Staff LLM Engineer — Agents & enterprise RAG Thames Inference Labs
Temps plein Staff Applied LLM Hybrid London, England, United Kingdom · Hybrid London, United Kingdom £120k–£155k + bonus + equity
Senior LLM Engineer — RAG & agents (contract-to-hire) Northbeam Inference Labs
Freelance Temps plein Senior Applied LLM Remote United States · Remote $170k–$220k + equity band · contractor ramp available
AI Developer — enterprise workflow agents ServiceNow
Temps plein Senior Now Assist Hybrid 2225 Lawson Lane, Santa Clara, CA 95054, United States · Hybrid Santa Clara, United States USD 155k–195k/year + equity
Ingénieur LLM — RAG enterprise LightOn
CDI (durée indéterminée) Temps plein Senior GenAI platform Hybrid 2 Rue de la Bourse, Paris, IDF 75002, France · Hybrid Paris, France EUR 70k–95k/year + BSPCE
Senior LLM Engineer — conversational AI (Remote US) Twilio
Temps plein Senior Customer AI Remote Remote · United States Remote, United States $170k–$230k + equity Voir toutes les offres →
Intitulé
Staff LLM Engineer — Agents & tool use
Postuler Pensé pour les équipes qui recrutent des personnes qui travaillent avec l’IA, pas seulement autour.
Les candidats voient compétences et outils dès le départ ; vous recevez des candidatures structurées dans un seul tableau de bord.
Touchez les praticiens IA qui parcourent les offres avec des attentes « preuve d’abord ».
Publier une offre Publiée le 10 mai 2026 Mise à jour le 3 juil. 2026
Thames Inference Labs ships assistant and RAG platforms for regulated customers in banking, insurance, and critical infrastructure. We blend pragmatic delivery with strong evaluation and rollback discipline so models never become a black-box liability.We are hiring a Staff LLM Engineer based in…
Avantages · Private medical, pension, learning budget, cycle scheme.
Python LangChain OpenAI API Vector DBs
Mise à jour le 3 juil. 2026
Northbeam Inference Labs — Own retrieval, chunking, and evaluation for customer-facing copilots. Ship tool-calling workflows, latency budgets, and rollback-safe prompt releases.Remote within US time zones; occasional on-site weeks in NYC.
Avantages · Health, 401k, home-office stipend, LLM API budget.
Python LangChain OpenAI API Vector DBs
ServiceNow Now Assist brings agents and copilots to IT and HR workflows. AI Developer implements retrieval, tool-use, and guardrails for enterprise tenants.Hybrid Santa Clara: multi-tenant isolation and audit trails are mandatory.What you will doShip RAG plugins and workflow automations on Now…
Avantages · Equity, hybrid South Bay.
Python LangChain OpenAI API
LightOn déploie des LLM souverains et des systèmes RAG enterprise pour des grands comptes européens depuis Paris.Ingénieur LLM RAG (hybride Paris 2e) : retrieval hybride, fine-tuning, évaluation qualité et mise en production sur modèles LightOn.À propos de LightOnScale-up française spécialisée…
Avantages · BSPCE, remote partiel, modèles souverains.
Python LangChain PyTorch OpenAI API
Twilio powers customer engagement APIs — voice, SMS, email, and AI agents — used by millions of developers worldwide.Senior LLM Engineer (Remote US): build conversational agents, agent assist, and knowledge retrieval for contact centers with strict latency and compliance needs.About TwilioPublic…
Avantages · All-remote US, equity, home office stipend.
Python LangChain NLP OpenAI API