Senior AI Explainability & Safety Researcher

microTECH Global LTD; Finland; Remote; EUR 90,000 - 130,000; Full time

Job summary

microTECH Global Limited is seeking a passionate researcher to advance state-of-the-art at the intersection of AI and safety. You will design architectures for detection systems that understand multimodal data, enabling robust reasoning over images, videos, text and knowledge graphs.

You will explore visual QA, reasoning, grounding, and neural-symbolic approaches, aiming for interpretable, unbiased and aligned AI. Production-ready tooling and collaboration with stakeholders are expected.

Qualifications

• Ph.D. in Computer Science, Deep Learning, Machine Learning, Mathematics or related fields.
• Strong track record in Explainable AI and Safety domains.
• Proficient with LLMs, neural networks, and computer vision; neuro-symbolic architectures.

Responsibilities

• Design and implement architecture for AI detection systems handling multimodal data.
• Explore visual QA, visual reasoning, text-based reasoning, and grounding using knowledge graphs and neural-symbolic methods.
• Develop interpretable AI techniques, aligned with human values for real-world scenarios.
• Create alignment methods (e.g., RLHF, RLAIF, Constitutional AI) for LLMs, CoT, and agentic workflows.
• Reverse-engineer neural networks to understand internal workings and implement explainability tools.
• Develop data attribution methods to quantify influence of data points on predictions.
• Build benchmarks/datasets to measure reasoning quality, explanations, transparency, and safety treatments.
• Defend against jailbreaking, prompt injections, and adversarial exploits targeting planning and tool-use.

Skills

Explainable AI

Safety

LLMs

Neural networks

Computer vision

Neuro-symbolic

AI alignment

Model robustness

Continual learning

Interpretability

Education

Ph.D. in Computer Science / ML / related field

Tools

Python

Java

C++

PyTorch

TensorFlow

Job description

microTECH Global Limited is seeking a passionate researcher to advance state-of-the-art at the intersection of AI and safety. You will design architectures for detection systems that understand multimodal data, enabling robust reasoning over images, videos, text and knowledge graphs.

You will explore visual QA, reasoning, grounding, and neural-symbolic approaches, aiming for interpretable, unbiased and aligned AI. Production-ready tooling and collaboration with stakeholders are expected.