Senior Researcher, Agentic Safety & Alignment

Helsinki, Finland (onsite)

We are partnering with a leading global technology organisation operating at the forefront of artificial intelligence research and large-scale model development. The team focuses on next‑generation AI systems with a strong emphasis on safety, reasoning robustness, and agentic intelligence.

The environment is highly research‑driven, combining foundational theoretical work with real‑world deployment of advanced AI systems at global scale.

Role Overview

We are seeking a Senior Researcher in Agentic AI Safety & Alignment to design and develop foundational methods that improve the safety, transparency, and robustness of large language model (LLM)-based agentic systems.

This role focuses on advancing alignment techniques, building evaluation and red‑teaming infrastructure, and transforming cutting‑edge AI safety research into scalable production systems. You will...