• Drive applied AI research and technical direction across retrieval and ranking systems for agent-native search.
• Design and evolve multi-stage retrieval architectures, including query understanding, query rewriting, reranking, and iterative retrieval.
• Develop approaches for grounding LLMs in real-time web data while maintaining quality, scalability, and reliability.
• Build and refine systems where LLMs can plan, query, evaluate, refine, and reason over retrieved information across multi-step workflows.
• Define new evaluation frameworks, metrics, and experimentation methodologies for agentic systems, recognizing that effectiveness cannot be measured solely through traditional click-based metrics.
• Lead experimentation with modern retrieval technologies, including embeddings, hybrid search, reranking, and related approaches, and transition successful methods into production.
• Analyze and manage trade-offs between relevance, latency, reliability, and infrastructure cost at scale.
• Partner closely with engineering teams to deploy AI and retrieval systems in high-throughput, low-latency production environments.
• Take ownership of ambiguous and complex technical problems from research through implementation and contribute to broader product and research direction.
• Mentor engineers, share technical expertise, and help raise the research and engineering standards of the team.

Requirements:

• 8+ years of experience in applied AI, machine learning, or software engineering.
• Proven track record of designing and shipping ML or AI systems into production at meaningful scale.
• Deep expertise in search, information retrieval, ranking, recommendation systems, assistants, or closely related domains.
• Strong understanding of modern deep learning, particularly transformer architectures and embeddings.
• Experience building LLM-integrated, knowledge-intensive, or retrieval-augmented systems.
• Practical experience designing evaluation frameworks and meaningful metrics for machine learning or AI systems.
• Strong programming skills in Python and proficiency in at least one additional language such as Go, C++, or a comparable systems-oriented language.
• Ability to operate effectively in a fast-moving, product-oriented environment with significant ownership and autonomy.
• Strong analytical and problem-solving abilities, with the ability to translate research concepts into reliable, measurable production systems.
• Experience with large-scale search or recommendation systems is an advantage.
• Background in agentic AI, including AI agents, tool use, autonomous workflows, or multi-step reasoning systems, is a plus.
• Experience with RAG, multi-step retrieval, or tool-enabled LLM applications is beneficial.
• Publications, open-source contributions, or other evidence of technical depth and research impact are welcome.

Benefits:

• Competitive compensation.
• Career growth and ongoing learning opportunities.
• High levels of flexibility, autonomy, and ownership.
• Opportunity to work on impactful applied AI projects at significant scale.
• Collaborative and innovative working environment.
• International team with highly experienced AI, engineering, and research professionals.
• Opportunity to influence technical direction and contribute to the development of emerging AI infrastructure and systems.
• Inclusive workplace with a commitment to equal employment opportunities and a diverse team environment.
• Support and reasonable accommodations throughout the application process where needed.
• Applicants must be authorized to work in the country where the position is based and may be required to provide proof of employment eligibility.