Senior Researcher – Explainable AI

You will be joining a world-leading technology company at their R&D site in Helsinki.

We are looking for an expert researcher to lead the charge in making artificial intelligence more understandable and ethically sound. This role focuses on deconstructing complex models to ensure they are transparent, fair, and perfectly synchronized with human expectations in practical applications.
 

Responsibilities

• Innovate for Transparency: Develop cutting-edge methodologies to improve model interpretability while eliminating bias and ensuring systems reflect human values.
• Bridge the Gap: Engineer solutions that ensure the explanations provided to users accurately mirror the actual internal logic of the model.
• Architectural Analysis: Perform deep-dive reverse engineering on neural networks to unlock the “black box” and understand their internal decision-making mechanics.
• Data Impact Assessment: Formulate data attribution strategies to determine exactly how specific inputs (text or imagery) influence a model’s final output.
• Framework Integration: Design and deploy specialized tools and techniques for AI explainability across various platforms.
• Benchmarking & Validation: Construct comprehensive datasets and rigorous testing standards to evaluate the effectiveness and honesty of model explanations.
• Stakeholder Engagement: Translate complex research findings into clear, actionable insights for diverse groups of stakeholders.

Qualifications

• PhD in Computer Science, Machine Learning, Deep Learning, Mathematics, or a relevant  field.
• Strong research background specifically within the domains of AI safety and explainability.
• Comprehensive knowledge of Large Language Models (LLMs), diverse neural network architectures, and computer vision systems.
• Expert-level programming skills (Python, C++, or Java) and deep familiarity with major frameworks like PyTorch or TensorFlow.
• Proven history of working with AI alignment, model robustness, and interpretability techniques is highly desired.
• Consistent track record of publishing original work in premier conferences like NeurIPS, ICLR, or ICML.
• Success in prestigious international challenges (e.g., ICPC, IMO, or IOAI) is viewed as a significant advantage.
• Desire to work in a multicultural setting and a drive to challenge traditional AI paradigms.

Benefits

• Annual Bonus
• Relocation Package
• Lunch Vouchers
• Equipment (laptop, etc.)