Staff Applied AI Researcher (Agentic Search)

Role overview Set applied AI research direction for an agent-focused search system that retrieves and evaluates live web information. You will own a key part of the search stack, such as ranking or iterative retrieval, and take new methods from research through production deployment under demanding latency, reliability, and scale constraints.

Responsibilities - Guide research and technical decisions across retrieval and ranking. - Design and evolve multi-stage search systems, including query understanding, rewriting, retrieval, reranking, and iterative search. - Experiment with embeddings, sparse and hybrid retrieval, reranking, and context compression, then bring effective approaches into production. - Develop ways to ground language models in current web data using signals for trustworthiness, quality, and freshness. - Work with evaluation specialists to define metrics for agent-driven systems where success cannot be measured by clicks alone. - Assess relevance, latency, and cost trade-offs; partner with engineers on deployment and mentor teammates.

Requirements - At least eight years of experience in applied AI, machine learning, or software engineering. - A track record of deploying ML or AI systems at scale. - Deep experience in search, retrieval, ranking, or retrieval-augmented assistants. - Strong knowledge of deep learning, especially transformers and embeddings. - Experience with language-model-based or knowledge-intensive systems and ML evaluation frameworks. - Strong Python programming skills and research publications at leading AI or machine learning conferences. - Ability to work with autonomy in a fast-moving, product-focused environment.

Nice to have - Experience with agentic AI, tool use, or autonomous workflows. - Experience with reinforcement learning post-training for language or vision-language models.

Benefits and work setup - The role is available in Amsterdam, London, Zurich, or remotely within Europe.