Staff AI Engineer - Build Scalable AI Agent Platform

JDA Software; Paris; Sur place; EUR 120 000 - 180 000; Plein temps

Résumé du poste

Blue Yonder is seeking a Staff AI Engineer to build the engineering foundations for AI-powered products in the Autonomy Labs. You will own architecture decisions, create robust systems, and enable scalable evaluation of agent behavior in real workflows.

You will collaborate with model-training teams and data engineers to deploy and continuously improve tools, traces, and performance while maintaining reliability and security across platforms.

Qualifications

• 8+ years of software engineering experience or equivalent depth.
• Strong Python and backend engineering expertise including API design and distributed systems.
• Hands-on experience building LLM-powered applications or AI agents.
• Practical understanding of AI evaluation, trace analysis, and regression testing.
• Security, observability, CI/CD, and reliable software practices.
• Experience with cloud platforms (Azure/AWS/GCP) and containerization.

Responsabilités

• Architect and build robust software systems for AI agents and evaluation pipelines.
• Develop services and pipelines for collecting agent traces, tool calls, and workflow outcomes.
• Create evaluation harnesses, regression tests, and training data for model improvements.
• Design reproducible environments with stable APIs, tools, and simulations.
• Collaborate with researchers to translate experiments into production evidence and feedback.

Connaissances

Python

Backend engineering

API design

Distributed systems

Automated testing

Observability

LLM-powered apps

AI agents

Model evaluation

Technical leadership

Outils

Azure

AWS

GCP

Docker

Kubernetes

Description du poste

Blue Yonder is seeking a Staff AI Engineer to build the engineering foundations for AI-powered products in the Autonomy Labs. You will own architecture decisions, create robust systems, and enable scalable evaluation of agent behavior in real workflows.

You will collaborate with model-training teams and data engineers to deploy and continuously improve tools, traces, and performance while maintaining reliability and security across platforms.