Senior Researcher: Explainable AI & Safety

Huawei; Helsinki; On-site; EUR 70,000 - 120,000; Full time

Benefits offered by this job

Culture & sports

Phone benefits

Team-building events

Office snacks

Job summary

Huawei Consumer Business Group's Cloud Content Security Lab in Helsinki seeks a passionate researcher to advance explainable AI and safety in large-scale models. You will design interpretable techniques and evaluate alignment with human values.

The role emphasizes AI explainability, safety, and collaboration with international teams. A PhD is required, with a strong publication record and hands-on experience in PyTorch or TensorFlow.

Qualifications

• Ph.D. in Computer Science, Deep Learning, ML, Mathematics or related field.
• Strong focus on AI with Explainable AI and Safety.
• Proficiency in LLMs, neural networks, and CV architectures.

Responsibilities

• Create methods to make AI models interpretable, unbiased, transparent and aligned with human values.
• Ensure alignment between explanations and model behavior.
• Reverse-engineer neural networks to understand internal workings.
• Develop data attribution methods to quantify influence on predictions.
• Implement and integrate AI explainability tools.
• Build benchmarks/datasets to measure explanations, transparency, and treatments.
• Communicate insights to stakeholders.

Skills

Explainable AI

AI safety

Interpretable ML

Neural networks

Computer vision

Education

PhD in Computer Science

Tools

PyTorch

TensorFlow

Python

Java

C++

Job description

Huawei Consumer Business Group's Cloud Content Security Lab in Helsinki seeks a passionate researcher to advance explainable AI and safety in large-scale models. You will design interpretable techniques and evaluate alignment with human values.

The role emphasizes AI explainability, safety, and collaboration with international teams. A PhD is required, with a strong publication record and hands-on experience in PyTorch or TensorFlow.