This list contains only the countries for which job offers have been published in the selected language (e.g., in the French version, only job offers written in French are displayed, and in the English version, only those in English).
Your career: In this role, you will act as the primary architect of the "nervous system" that bridges the gap between sophisticated AI models and real-world business logic. You will design and maintain the critical infrastructure that enables intelligent, autonomous features to function reliably at scale, moving beyond simple API wrappers to build deeply integrated AI systems. You will take ownership of the entire data flow, where you will develop high-performance RAG (Retrieval-Augmented Generation) pipelines and complex agentic workflows that provide users with accurate, context-aware responses. Your Impact: Champion system stability by implementing rigorous evaluation and monitoring frameworks, ensuring that as our AI capabilities grow, our production environment remains fast, cost-effective, and secure. Ultimately, you will be the technical force that transforms cutting-edge AI research into stable, scalable products that define the future of our platform.
Job Responsibility:
Act as the primary architect of the "nervous system" that bridges the gap between sophisticated AI models and real-world business logic
Design and maintain the critical infrastructure that enables intelligent, autonomous features to function reliably at scale
Take ownership of the entire data flow, where you will develop high-performance RAG (Retrieval-Augmented Generation) pipelines and complex agentic workflows
Champion system stability by implementing rigorous evaluation and monitoring frameworks
Requirements:
Keeps up with the latest research and stays on top of the fast-moving AI space, with a real passion for what’s happening in Generative AI
Regularly tries out different AI tools and sees how they’re useful in everyday work and life
Strong understanding of advanced prompting techniques like Chain-of-Thought, ReAct, and few-shot prompting
Experience working on model quantization or finding ways to optimize inference costs and token usage at scale
Hands-on experience with Python (FastAPI, Django, or Flask) or Go, with a solid grasp of async programming and microservices
Experience turning a vague product idea (e.g., "let's add a smart assistant") into clear, concrete technical requirements
Hands-on experience using frameworks like LangChain to build more complex LLM flows and agents
Experience working with vector databases
Comfortable building and using RESTful and GraphQL APIs, especially when dealing with low-latency streaming (WebSockets, Server-Sent Events)
Enjoys digging into "non-deterministic" systems - when an LLM fails, comfortable figuring out whether it’s the prompt, the retrieval, or the data
Familiar with AI-specific security risks, like prompt injection and data leakage
Nice to have:
Hands-on experience using frameworks like LangChain to build more complex LLM flows and agents
Experience working with vector databases
Comfortable building and using RESTful and GraphQL APIs, especially when dealing with low-latency streaming (WebSockets, Server-Sent Events)
Enjoys digging into "non-deterministic" systems - when an LLM fails, comfortable figuring out whether it’s the prompt, the retrieval, or the data
Familiar with AI-specific security risks, like prompt injection and data leakage