Senior AI Engineer

Founded in 2009, XM is a global leader in shaping the future of online trading and driving tech-powered financial innovation. With over 1,700 experts working collaboratively across multiple offices and remote locations worldwide, the XM Group is committed to staying at the forefront of its industry. Headquartered in Cyprus, XM drives innovation by incorporating cutting-edge technologies including AI and state-of-the-art tools, delivering exceptional services for its over 20 million clients worldwide, all while transforming the work experience for its dynamic global team. Guided by its core values, Big. Fair. Human., XM is consistently being recognised with international distinctions, including Great Place To Work® certifications for offering world-class benefits that prioritise both the personal and professional success of its employees. For the second consecutive year, XM is proud to be among the 2025 Fortune 100 Best Companies to Work For™ in Europe, a remarkable achievement that reflects our commitment to creating a truly exceptional workplace experience.

• BSc/MSc in Computer Science, Engineering, or a related field.
• 5+ years of professional experience in backend development using Golang (preferred), Java, or Python.
• 2+ years of hands-on experience developing and deploying production GenAI applications.
• Strong understanding of vector databases and semantic retrieval techniques.
• Practical experience with LLMs and prompt engineering, including APIs and tools.
• Experience with agentic architectures and AI orchestration frameworks such as LangChain or Genkit.
• Solid understanding of the full software development life cycle including CI/CD pipelines, testing, and cloud deployment.
• Experience working in cross-functional teams with product and program managers.
• Experience optimizing, monitoring, and testing LLM-based applications.
• Passion for emerging GenAI technologies and innovation.
• Strong teamwork, collaboration skills, and a proactive mindset.
• Commitment to continuous learning.

Nice to have:

• Experience with AWS Cloud Services (EC2, S3, SQS).
• Knowledge of LLM observability frameworks (e.g., LangFuse) and tracing tools.
• Experience building pipelines for model evaluation, feedback collection, and continuous improvement.
• Portfolio of open-source contributions, side projects, or technical blogs showcasing AI or backend expertise.

• Design, develop, and maintain intelligent backend systems combining LLMs, retrieval systems, and custom APIs ensuring high performance, scalability, and reliability.
• Participate in team discussions and conduct code reviews to ensure code quality, security, maintainability, and best practices including testing, CI/CD, observability, and documentation.
• Propose, research, and integrate new generative AI technologies such as vector databases, agent frameworks, and LLM observability tools.
• Collaborate cross-functionally with front-end developers, data scientists, and product managers to define requirements and deliver end-to-end solutions.
• Monitor and improve existing AI systems focusing on optimization, cost efficiency, and performance enhancement.