Senior Researcher (Explainable AI) - Helsinki (Perm)

microTECH Global Limited; Helsinki; Hybrid; EUR 70,000 - 110,000; Full time

Job summary

microTECH Global Limited in Helsinki seeks a passionate researcher with a solid track record of solving challenging problems, advancing state-of-the-art methods, and a demonstrated drive to scale ideas to production in the AI and Safety domain.

You will create techniques for interpretable, unbiased, and aligned models; reverse-engineer neural networks; develop data attribution methods; implement explainability tools; build benchmarks; and clearly communicate insights to stakeholders.

Qualifications

• PhD in CS/ML/Math or related field.
• Strong publication record in top venues (e.g., NeurIPS/ICLR/ICML/ AAAI/ACL...).
• Experience with LLMs, neural networks, and computer vision architectures.
• Proficiency in Python, Java, or C++, with ML frameworks (PyTorch, TensorFlow).
• Experience with AI alignment, model robustness, continual learning, interpretability and editing techniques.
• International competition experience valued.

Responsibilities

• Create new techniques to make AI models more interpretable, unbiased, transparent and aligned with human values for real-world scenarios.
• Create techniques to ensure alignment between explanations and model behavior.
• Reverse-engineer neural networks to understand internal workings.
• Develop data attribution methods to quantify influence of data points on predictions.
• Implement and integrate AI explainability tools and techniques.
• Build rigorous benchmarks and datasets to measure explanations and transparency.
• Communicate insights to stakeholders.

Skills

Explainable AI

AI safety focus

Research leadership

Education

PhD in Computer Science or related field

Tools

PyTorch

TensorFlow

CUDA

Job description

We are looking for a passionate and motivated researcher with a solid track record of solving challenging problems, advancing state-of-the-art, and demonstrated passion for ground-breaking research that could be scaled to production environment with an emphasis on the intersection of AI and Safety.

Your responsibilities:

• Create new techniques to make AI models more interpretable, unbiased, transparent and aligned with human values for real-world scenarios.
• Create new techniques to ensure consistent alignment between user-centric explanations and intrinsic model behavior.
• Reverse-engineer on neural networks to understand internal workings of AI models rather than treating them as "black boxes".
• Develop data attribution methods to quantify the influence of specific data points (text and image) on a model's prediction and implement solution.
• Implement and integrate AI explainbility techniques and tools.
• Build rigorous benchmarks and datasets to measure the quality of explanations, model transparency, and effectiveness of treatments.
• Communicate insights to stakeholders.

Requirements:

• Ph.D. in Computer Science, Deep Learning, Machine Learning, Mathematics or other related fields.
• Focused on research in the AI field with good track records and high motivation in Explainable AI and Safety domain.
• Strong proficiency in Large Language Models (LLMs), neural networks, and computer vision architectures.
• Strong background in Python, Java, or C++, with deep knowledge of ML frameworks such as PyTorch, TensorFlow.
• Successful experience in AI alignment to human values and expectations, model robustness improvement, controlled and continual learning, neural network interpretability and editing techniques is highly valued.
• Pioneering novel methods and neural networks that revolutionized machine learning or the AI field, or revolutionized the industry, is a big bonus.
• Strong publication record in top conferences (i.e. NeurIPS/ICLR/ICML/ AAAI/ACL/CVPR/ICCV/EMNLP/NAACL).
• Candidates with ICPC, IOI/IMO, IOAI and other international competition in computer science, machine learning, and AI, etc. are highly preferred.
• Good teamwork, enjoy working with multi‑culture teams, passionate in challenging the status quo.