Senior Data Scientist | AI Security & Generative AI

Senior Data Scientist | AI Security & Generative AI

The company is developing a new generation of advanced AI Agents designed to operate in complex environments and provide intelligent, context-aware responses at a human level. The project combines cutting-edge research and hands-on development across Generative AI, Natural Language Processing, Large Language Models, Agentic Systems, and AI Security.

The Senior Data Scientist will join the core R&D team and take a significant role in the research, design, development, evaluation, and security of advanced AI and LLM-based systems. This is a deeply technical position intended for an experienced Data Scientist who is comfortable moving between research, algorithm development, experimentation, and implementation of production-ready solutions.

A major focus of the project is the development of LLM-based and Multi-Agent Systems capable of handling complex, multi-step tasks. The role includes researching and designing agent architectures, improving reasoning and decision-making mechanisms, developing orchestration approaches between multiple agents, and evaluating the performance, reliability, and robustness of these systems.

Another core area is NLP and LLM algorithm development. The Senior Data Scientist will research and implement advanced approaches involving Transformer architectures, model training and fine-tuning, embeddings, retrieval mechanisms, reranking, and other techniques aimed at improving model accuracy, contextual understanding, and overall performance.

The project also places strong emphasis on AI Evaluation and Reliability. The role involves designing rigorous evaluation methodologies and frameworks for Generative AI systems, defining relevant metrics, developing automated evaluation pipelines, and analyzing model behavior across different scenarios. This includes identifying and measuring hallucinations, bias, safety issues, reliability problems, and unexpected model behavior.

A central component of the position is AI Security. The Senior Data Scientist will research potential attack vectors against LLMs and AI Agents and develop methods for identifying, evaluating, and mitigating these threats. This includes working with areas such as Prompt Injection, Jailbreaks, Adversarial Attacks, model manipulation, and other emerging attack techniques targeting Generative AI systems.

The role will also involve Red Teaming of AI systems, actively testing models and agents from an attacker’s perspective in order to expose vulnerabilities, understand failure modes, and develop effective defense and model-hardening mechanisms. The goal is not only to identify weaknesses, but to translate these findings into algorithms, safeguards, evaluation methodologies, and architectural improvements.

• Research, design, and develop advanced Machine Learning, NLP, and Generative AI algorithms.
• Develop and optimize LLM-based solutions and Transformer-based architectures.
• Design and implement Multi-Agent Systems for complex reasoning and multi-step tasks.
• Research and improve agent orchestration, reasoning, decision-making, and interaction mechanisms.
• Develop advanced Retrieval, Embedding, and Reranking approaches.
• Design and implement comprehensive evaluation frameworks for LLMs and AI Agents.
• Define metrics and methodologies for measuring model quality, reliability, robustness, and safety.
• Identify, analyze, and measure hallucinations, bias, safety risks, and abnormal model behavior.
• Research vulnerabilities and attack vectors affecting LLMs and Agentic Systems.
• Analyze and develop defenses against Prompt Injection, Jailbreaks, Adversarial Attacks, and other AI-specific threats.
• Conduct Red Teaming and adversarial testing of AI models and agents.
• Develop model-hardening mechanisms and security safeguards.
• Conduct experiments, analyze results, and translate findings into algorithmic and architectural improvements.
• Read and analyze state-of-the-art academic research and convert relevant approaches into working implementations.
• Take solutions through the full lifecycle — from research and experimentation through model development, evaluation, optimization, and production.
• Collaborate closely with research, engineering, product, and senior leadership teams.

• 7+ years of hands-on experience in Data Science, Machine Learning, or algorithm development.
• B.Sc. or M.Sc. in Computer Science, Mathematics, Data Science, Engineering, or another relevant quantitative field.
• Strong hands-on experience developing Machine Learning models end-to-end, including training, experimentation, evaluation, optimization, and production deployment.
• Significant practical experience with NLP, Large Language Models, and Generative AI.
• Deep understanding of Transformer architectures and modern NLP methodologies.
• Strong Python development skills.
• Hands-on experience with PyTorch.
• Experience researching, developing, or evaluating LLM-based systems.
• Practical experience in AI Security and/or Cyber Security.
• Experience identifying, analyzing, or mitigating attacks against AI models.
• Knowledge and practical experience in AI Safety, Bias Detection, model robustness, and AI Evaluation.
• Strong research capabilities, including the ability to understand academic papers, evaluate proposed methodologies, and translate research into working code.
• Strong algorithmic and analytical thinking with the ability to investigate complex model behavior and identify root causes.

• Experience conducting AI Red Teaming or adversarial testing.
• Experience with Adversarial Machine Learning and Adversarial Attacks.
• Hands-on experience with Prompt Injection and Jailbreak detection or mitigation.
• Experience developing model-hardening and AI defense mechanisms.
• Experience designing or developing Multi-Agent Systems.
• Experience with advanced LLM evaluation methodologies.
• Experience working with large-scale datasets and complex production AI environments.
• Background in advanced algorithmic or applied AI research.
• Previous experience in large technology companies, research organizations, or data-intensive environments.

We are looking for a highly technical and research-oriented Senior Data Scientist who combines strong Machine Learning and NLP foundations with the ability to think critically about how AI systems behave, fail, and can be attacked.

The ideal candidate is someone who does not treat an LLM as a black box, but is interested in understanding its architecture, behavior, limitations, vulnerabilities, and failure modes — and is capable of translating that understanding into better algorithms, stronger evaluation methodologies, and more secure AI systems.

• This position is particularly suited to someone who enjoys working at the intersection of AI Research, Algorithm Development, Generative AI, Agentic Systems, and AI Security, and wants to have a significant technical impact on the development of advanced AI systems.