Staff Applied AI Researcher (Agentic Search)

Accountabilities:: Drive applied AI research and define the technical direction of advanced retrieval and ranking systems within an agent-native search architecture. Design and develop intelligent search capabilities that support everything from low-latency, single-step queries to complex deep-search tasks involving iterative planning, information retrieval, refinement, and reasoning. Build, train, and optimise machine learning models for retrieval and ranking, specifically designed for agent-driven workflows and real-world production constraints. Design and continuously improve multi-stage retrieval architectures, including query understanding, query rewriting, information retrieval, reranking, and iterative retrieval processes. Lead experimentation with advanced information retrieval techniques, including embedding models, sparse and hybrid retrieval, reranking strategies, and context compression. Translate emerging research developments into practical solutions, integrating promising approaches into production systems and evaluating their measurable impact. Develop innovative methods for grounding large language models (LLMs) in real-time web data, using trustworthiness, content quality, and freshness signals to identify and prioritise reliable information sources. Collaborate with evaluation specialists to design new metrics and assessment frameworks for agentic search systems, addressing performance dimensions that extend beyond traditional click-based measurements. Analyse and optimise trade-offs between search relevance, response latency, computational costs, and system reliability. Work closely with engineering teams to deploy, scale, and maintain robust search systems capable of supporting high-volume production workloads. Provide technical mentorship to researchers and engineers, sharing expertise and helping establish high standards for research quality and engineering excellence. Take ownership of key components of the search technology stack, defining research priorities, architectural decisions, and development roadmaps. Requirements: At least 8 years of professional experience in applied artificial intelligence, machine learning, or software engineering, with a strong focus on developing advanced technical solutions. Proven track record of successfully designing, developing, and deploying machine learning or AI systems into large-scale production environments. Deep expertise in information retrieval, search technologies, ranking systems, or retrieval-augmented generation (RAG) assistants. Strong understanding of modern deep learning techniques, particularly transformer architectures, embedding models, and their applications in information retrieval. Demonstrated experience building LLM-integrated applications or knowledge-intensive AI systems. Previous experience designing evaluation frameworks, performance benchmarks, and metrics for machine learning systems. Advanced programming skills in Python, with the ability to develop, test, and optimise complex AI and machine learning solutions. Strong academic research background, supported by publications in leading AI and machine learning conferences such as ICLR, ICML, NeurIPS, AAAI, EMNLP, or ACL. Ability to translate theoretical research and emerging AI developments into practical, production-ready applications. Strong analytical and problem-solving abilities, with a deep understanding of system performance, scalability, relevance, and computational efficiency. Excellent communication and collaboration skills, with the ability to work effectively across research and engineering teams. Proven ability to mentor technical professionals and influence research and engineering direction. Comfortable operating in a fast-paced, product-driven environment, demonstrating a high level of ownership, independence, and accountability. Experience with agentic AI systems, including autonomous agents, tool usage, and multi-step workflows, is a strong advantage. Familiarity with reinforcement learning post-training techniques for large language models (LLMs) or vision-language models (VLMs) is considered an additional asset. Benefits: Fully remote working arrangement within Europe. Opportunity to contribute to the development of next-generation agent-native search technology. Significant ownership over applied AI research priorities, technical architecture, and key components of the search platform. Opportunity to work on complex, large-scale AI challenges involving real-time information retrieval, ranking, and autonomous reasoning. Exposure to cutting-edge developments in machine learning, LLMs, retrieval-augmented generation, and agentic AI. Direct opportunity to translate innovative research into production systems serving substantial real-world workloads. Collaborative environment bringing together experienced AI researchers, machine learning specialists, and software engineers. Opportunity to mentor technical colleagues and influence research standards and engineering practices. High-autonomy position within a fast-growing, product-driven technology environment. Professional growth through challenging research initiatives and exposure to emerging AI technologies.