AI Engineer - Self-Hosted LLMs & High-Performance Inference

In Tandem; Paris; Sur place; EUR 60 000 - 80 000; Plein temps

Résumé du poste

In Tandem, located in Paris, is seeking a skilled AI infrastructure engineer to manage and optimize self-hosted LLMs while building efficient AI features. The role emphasizes hands-on work with real systems and requires 5+ years of experience shipping production software, particularly in AI/ML.

The successful candidate will collaborate with feature teams to develop innovative solutions that support families through app-enhancements. The position offers a competitive salary ranging from €60,000 to €80,000 annually, with a focus on remote work in a dynamic environment.

Qualifications

• 5+ years shipping production software with applied AI/ML experience.
• Experience with self-hosted LLMs on multi-GPU hardware.
• Strong fundamentals in Python and full-stack development.

Responsabilités

• Run and optimize self-hosted inference stack for AI workloads.
• Build efficient and observable AI features.
• Collaborate closely with feature owners to prototype and ship products.

Connaissances

Hands-on infrastructure experience

Production software shipping (5+ years)

Optimizing LLMs

Strong Python skills

DevOps (Docker, CI/CD)

Outils

AWS

Docker

TensorRT

LangGraph

Description du poste

In Tandem, located in Paris, is seeking a skilled AI infrastructure engineer to manage and optimize self-hosted LLMs while building efficient AI features. The role emphasizes hands-on work with real systems and requires 5+ years of experience shipping production software, particularly in AI/ML.

The successful candidate will collaborate with feature teams to develop innovative solutions that support families through app-enhancements. The position offers a competitive salary ranging from €60,000 to €80,000 annually, with a focus on remote work in a dynamic environment.