AI Engineer

BeTomorrow – SARL; Bordeaux; Sur place; EUR 60 000 - 80 000; Plein temps

Résumé du poste

BeTomorrow – SARL is seeking an experienced professional to join its AI team in Bordeaux. The role involves designing and developing generative AI solutions for diverse sectors, including luxury and healthcare.

The ideal candidate will have a minimum of 5 years in software development, focusing on production LLM systems, and be adept in using tools like Python and AWS. Responsibilities include optimizing AI solutions for performance and integrating them into robust applications.

Qualifications

• Minimum 5 years of software development experience.
• Experience delivering generative AI solutions in production.
• Strong expertise with production LLM systems and prompt engineering.

Responsabilités

• Design and build production-ready LLM pipelines.
• Develop RAG architectures and autonomous AI agents.
• Optimize cost, latency, and performance of AI systems.

Connaissances

Generative AI solutions

Production LLM systems

Python

Software engineering

Cloud services (AWS, Azure, GCP)

Outils

LangChain

FastAPI

PostgreSQL

Description du poste

About BeTomorrow

BeTomorrow is a digital product agency based in Bordeaux, France. For more than 20 years, our team of 70 passionate experts has been designing and building impactful digital products across web, mobile, AI and data. We combine technical excellence, product thinking and agile ways of working to create meaningful digital experiences.

Some of our achievements include:

• Live sports tracking solutions for PMU
• Augmented reality experiences for sailing events, including the Olympic Games
• The official G20 application for the European Union
• The TBM mobility application

We also develop our own AI products, including:

• ALLY, an AI-powered mobility platform
• Planéa, an AI companion for architects

As part of our AI team in Bordeaux, you will lead the design, development and industrialization of generative and agentic AI solutions for clients across luxury, healthcare, entertainment, industry and mobility sectors.

What you’ll do

• Design and build production-ready LLM pipelines
• Develop RAG architectures and autonomous AI agents
• Implement multi‑agent orchestration systems
• Industrialize AI solutions through deployment, monitoring and optimization
• Integrate AI capabilities into robust applications and backend services
• Make architecture decisions, including model selection and RAG vs fine‑tuning trade‑offs
• Design evaluation frameworks, benchmark datasets and regression testing strategies
• Optimize cost, latency and performance of AI systems
• Contribute to the growth of the AI practice through mentoring, knowledge sharing and continuous technology watch

Our technology stack

AI & LLM

• Python
• LangChain
• Google ADK
• Vertex AI
• Azure AI Services

Backend

• FastAPI
• Spring Boot (Kotlin)
• NestJS

Data

• PostgreSQL
• MySQL
• Firestore
• Vector databases

Cloud & DevOps

• AWS
• Azure
• Google Cloud Platform
• Terraform
• GitLab CI/CD

What we’re looking for

• Minimum 5 years of software development experience
• Proven hands‑on experience delivering generative AI solutions in production
• Strong expertise with production LLM systems: RAG, prompt engineering, AI agents, function calling
• Experience evaluating and monitoring AI systems: evaluation datasets, quality metrics, observability
• Strong software engineering foundations: Python, testing, CI/CD, containerization, software craftsmanship
• Experience with at least one major cloud provider (AWS, Azure or GCP) and its AI services
• Strong focus on code quality, maintainability and long‑term scalability
• Comfortable using AI‑assisted development tools such as GitHub Copilot, Claude or Cursor while maintaining sound engineering judgment

Nice to have

• MLOps and model industrialization experience (MLflow, Vertex AI, etc.)
• Deep learning expertise (PyTorch, TensorFlow)
• Fine‑tuning experience
• Interest in Green AI and responsible AI practices