As a Staff Applied AI Researcher, you will drive research strategy and technical development across agent-native search systems, ensuring that innovative approaches deliver reliable results in demanding production environments.

• Lead applied AI research and define the technical direction of retrieval and ranking systems.

• Design and evolve multi-stage retrieval architectures covering query understanding, query rewriting, retrieval, reranking, and iterative retrieval.

• Develop agent-native search capabilities supporting both low-latency, single-step queries and complex research tasks involving iterative planning, querying, and reasoning.

• Lead experimentation with advanced retrieval techniques, including embedding research, sparse and hybrid retrieval, reranking, and context compression.

• Train and optimize ranking and retrieval models specifically designed for agent-driven workflows and real-world production constraints.

• Develop approaches for grounding large language models (LLMs) in real-time web data at scale, incorporating trust, quality, and freshness signals to identify reliable sources.

• Collaborate with evaluation teams to develop new metrics and assessment frameworks for agentic systems, moving beyond traditional click-based performance indicators.

• Analyze and optimize trade-offs between search relevance, system latency, operational reliability, and computational costs.

• Partner closely with engineering teams to deploy, scale, and maintain advanced AI search capabilities across production workloads.

• Translate the latest advances in AI and machine learning research into practical solutions with measurable production impact.

• Mentor researchers and engineers, promote technical excellence, and contribute to the team's long-term research strategy.

• Take ownership of a key component of the search stack, such as ranking or iterative retrieval, and drive its development throughout the first year.

Requirements:

You are an experienced applied AI researcher or machine learning engineer with a strong research background and a proven ability to turn sophisticated technical ideas into production-ready systems.

• At least 8 years of experience in applied AI, machine learning, or software engineering.

• Demonstrated track record of designing, developing, and deploying machine learning or AI systems at scale.

• 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 and embedding models.

• Experience building or developing LLM-integrated systems and knowledge-intensive applications.

• Proven experience designing evaluation frameworks, performance metrics, and experimentation methodologies for machine learning systems.

• Strong programming skills in Python and the ability to build robust, scalable technical solutions.

• Publications in leading AI and machine learning conferences, such as ICLR, ICML, NeurIPS, AAAI, EMNLP, or ACL.

• Ability to operate effectively in a fast-paced, product-driven environment with a high degree of ownership and autonomy.

• Strong analytical and problem-solving skills, with the ability to balance research innovation against practical engineering constraints.

• Excellent collaboration and communication skills, particularly when working across research and engineering teams.

Nice-to-Have Qualifications:

• Experience developing agentic AI systems, including autonomous agents, tool use, and multi-step workflows.

• Familiarity with reinforcement learning post-training techniques for large language models (LLMs) or vision-language models (VLMs).

Benefits:

• High-impact research ownership: Shape the applied AI research direction and influence the architecture of next-generation agentic search systems.

• End-to-end technical responsibility: Own a critical component of the search stack and take innovations from research through production deployment.

• Advanced AI challenges: Work on cutting-edge retrieval, ranking, and reasoning problems involving real-time web data and large-scale AI workloads.

• Research-driven environment: Apply the latest advances from the global AI research community to real-world products.

• Technical leadership opportunities: Mentor researchers and engineers while helping establish high technical standards.

• International work environment: Opportunities based in Amsterdam, London, Zurich, or remotely within Europe.

• High ownership and autonomy: Work in a fast-moving, product-oriented environment where your research and technical decisions have a direct impact.