Agentic Reasoning & AI Safety Research Scientist

microTECH Global LTD; Helsinki; On-site; EUR 80,000 - 120,000; Full time

Job summary

microTECH Global LTD is seeking an experienced AI safety researcher to advance state‑of‑the‑art methods for multi‑modal data, reasoning and alignment. You will design architectures that enable robust detection and analysis, exploring neural-symbolic approaches, knowledge grounding and interpretable AI techniques.

The role emphasizes publishing results, building scalable production‑ready tooling, and collaborating with cross‑cultural teams to push the boundaries of responsible AI and safety in

Qualifications

• PhD in CS/ML or related field.
• Proven track record in AI safety or explainable AI.
• Strong programming experience in Python and ML frameworks.

Responsibilities

• Design and implement novel AI safety research architectures.
• Develop scalable tools for AI detection and reasoning across modalities.
• Collaborate with diverse teams to translate research into production.

Skills

LLMs/VLMs

Neural networks

Explainable AI

Python

PyTorch

TensorFlow

Knowledge graphs

Safety alignment

Multimodal reasoning

Education

PhD in CS/ML

Tools

PyTorch

TensorFlow

Keras

scikit-learn

Job description

microTECH Global LTD is seeking an experienced AI safety researcher to advance state‑of‑the‑art methods for multi‑modal data, reasoning and alignment. You will design architectures that enable robust detection and analysis, exploring neural-symbolic approaches, knowledge grounding and interpretable AI techniques.

The role emphasizes publishing results, building scalable production‑ready tooling, and collaborating with cross‑cultural teams to push the boundaries of responsible AI and safety in