Explainable AI Researcher for Safe, Transparent Models

microTECH Global LTD; Helsinki; On-site; EUR 90,000 - 130,000; Full time

Job summary

microTECH Global LTD is seeking a passionate researcher to tackle challenging AI safety problems at the intersection of AI and safety, with a track record of advancing state-of-the-art and scaling research toward production.

You will develop interpretable, unbiased models, improve alignment with human values, and communicate insights to stakeholders.

Ph.D. plus publications and strong ML background required; collaboration in multi-cultural teams is encouraged.

Qualifications

• Ph.D. in Computer Science, ML, or related fields.
• Research focus in AI explainability and safety.
• Strong proficiency with LLMs, neural networks, and CV architectures.
• Solid Python, Java, or C++ with ML frameworks PyTorch and TensorFlow.
• Experience in AI alignment, model robustness, and continual learning.
• Publications in top conferences are highly valued.
• International competition experience is a plus.
• Good teamwork and cross-cultural collaboration.

Responsibilities

• Create interpretable, unbiased AI techniques for real-world scenarios.
• Align explanations with intrinsic model behavior for user-centric transparency.
• Reverse-engineer neural networks to understand internals.
• Develop data attribution methods to quantify data influence on predictions.
• Implement and integrate AI explainability tools and benchmarks.
• Build rigorous benchmarks and datasets to measure explanations and transparency.
• Communicate insights to stakeholders.

Skills

Explainable AI

AI safety

LLMs

Neural networks

Computer vision

Python/Java/C++

ML frameworks

Team collaboration

Research communication

Education

Ph.D. in Computer Science or ML

Tools

PyTorch

TensorFlow

Job description

microTECH Global LTD is seeking a passionate researcher to tackle challenging AI safety problems at the intersection of AI and safety, with a track record of advancing state-of-the-art and scaling research toward production.

You will develop interpretable, unbiased models, improve alignment with human values, and communicate insights to stakeholders.

Ph.D. plus publications and strong ML background required; collaboration in multi-cultural teams is encouraged.