Explainable AI Researcher: Interpretable & Safe Models

microTECH Global LTD; Helsinki; On-site; EUR 70,000 - 110,000; Full time

Job summary

microTECH Global LTD is seeking a passionate researcher to advance AI and Safety across production-ready systems. Responsibilities focus on interpretability, alignment with human values, and robust model explanations.

The role requires strong publication records and collaboration in multidisciplinary teams. Candidate will explore novel methods in AI alignment, robustness, and explainability, with an emphasis on scaling techniques from research to production environments.

Qualifications

• Ph.D. in Computer Science, Deep Learning, ML, Mathematics or related field.
• Research focus in AI with strong motivation in Explainable AI and Safety domain.
• Proficient with Large Language Models, neural networks, and computer vision architectures.

Responsibilities

• Create new techniques to improve AI interpretability, bias reduction, transparency and alignment with human values for real-world scenarios.
• Ensure alignment between user explanations and intrinsic model behavior.
• Reverse-engineer neural networks to understand internal workings rather than treating them as black boxes.
• Develop data attribution methods to quantify influence of data points on predictions.
• Implement and integrate AI explainability techniques and tools.
• Build rigorous benchmarks and datasets to measure explanations, transparency, and treatment effectiveness.
• Communicate insights to stakeholders.

Skills

Interpretable AI

Explainable AI

LLMs

Neural networks

Computer vision

Python

Java

C++

PyTorch

TensorFlow

AI alignment

Model robustness

Continual learning

Education

PhD in CS/ML/Math

Tools

PyTorch

TensorFlow

Job description

microTECH Global LTD is seeking a passionate researcher to advance AI and Safety across production-ready systems. Responsibilities focus on interpretability, alignment with human values, and robust model explanations.

The role requires strong publication records and collaboration in multidisciplinary teams. Candidate will explore novel methods in AI alignment, robustness, and explainability, with an emphasis on scaling techniques from research to production environments.