Machine Learning (Explainable AI)

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

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.

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.