Senior Researcher, Neurosymbolic Reasoning

Enko; Helsinki; On-site; EUR 90,000 - 150,000; Full time

Job summary

Enko Group in Helsinki is seeking a Senior Researcher, Neurosymbolic Reasoning to advance AI detection systems that reason over multimodal data. You will push neuro-symbolic AI, alignment and explainability for real-world deployments.

Design novel architectures, develop robust benchmarks, and collaborate with multicultural teams to translate breakthroughs into scalable tools for our client. On-site in Helsinki; PhD and strong publication record required.

Qualifications

• Ph.D. in Computer Science, Deep Learning, Machine Learning, Mathematics or related fields.
• Focused on AI research with strong motivation in Explainable AI and Safety.
• Strong proficiency in LLMs, neural networks, and computer vision, neuro-symbolic architectures.
• Background in Python, Java, or C++, with ML frameworks such as PyTorch, TensorFlow.
• Experience in AI alignment, model robustness, continual learning and interpretability.
• Strong publication record in top conferences (NeurIPS, ICLR, ICML, AAAI, ACL, CVPR, ICCV, EMNLP, NAACL).
• Team player in multicultural environments.

Responsibilities

• Design and implement architecture to enable AI detection systems that reason over multimodal data.
• Explore visual QA, visual reasoning, text-based reasoning, and multimodal grounding with knowledge graphs.
• Develop interpretable, unbiased, transparent AI aligned with human values for real-world use.
• Align LLMs and multi-step reasoning with CoT, agentic workflows and explanations.
• Reverse-engineer neural networks and implement explainability tools.
• Develop data attribution methods to quantify influence of data points on predictions.
• Create benchmarks and datasets to measure reasoning quality, explanations, and reliability.
• Build defenses against jailbreaking, prompt injections, and adversarial exploits.
• Communicate insights to stakeholders and turn research into production-ready tools.

Skills

LLMs

Neural networks

Computer vision

Neuro-symbolic architectures

Python

PyTorch

TensorFlow

Education

Ph.D. in Computer Science or related field

Tools

PyTorch

TensorFlow

Job description

Enko Group is recruiting a Senior Researcher, Neurosymbolic Reasoning for our client, a leading global technology company with an R&D center in Helsinki.

Job Description

• Design and implement effective, efficient and novel architecture to enable AI detection system that understands and able to reason over complex multimodal data, such as images, videos, text and cultural knowledge.

• Explore novel techniques for visual question answering, visual reasoning, text-based reasoning, and multimodal knowledge grounding. Explore the use of knowledge graphs and other neural-symbolic techniques to enhance reasoning capabilities.

• Create new techniques to make AI models/Agentic AI system 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. Develop and implement state-of-the-art alignment techniques (e.g., RLHF, RLAIF, Constitutional AI) specifically tailored for LLMs CoT, agentic workflows and multi-step reasoning.

• Reverse-engineer on neural networks to understand internal workings of AI models rather than treating them as "black boxes". Implement and integrate AI explainbility techniques and tools.

• Develop data attribution methods to quantify the influence of specific data points (text and image) on a model's prediction and implement solution.

• Build rigorous benchmarks and datasets to measure the quality of reasoning capabilities and reliability, quality of user-centric explanations, model transparency, and effectiveness of treatments.

• Develop robust defenses against jailbreaking, prompt injections, and adversarial exploits that target a model’s planning and tool-use capabilities.

• Communicate insights to stakeholders.

• Turn cutting-edge AI detections and AI safety papers into high-performance, scalable code, transforming theoretical breakthroughs into production-ready tools and frameworks.

Qualifications & 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, neuro-symbolic 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.

• Strong publication record in top conferences (i.e. NeurIPS/ICLR/ICML/ AAAI/ACL/CVPR/ICCV/EMNLP/NAACL).

• Pioneering novel methods and neural networks that revolutionized machine learning or the AI field, or revolutionized the industry, is a big bonus.

• Good teamwork skills and enjoy working in multicultural teams.

Location & Employment

The position is based on-site in Helsinki, Finland.

This is a full-time consultant position. You will be employed by Enko Group and work as a consultant for our client.