Principal AI Researcher, Agentic Retrieval & LLM Systems

Nebius; United States; Remote; USD 180,000 - 280,000; Full time

Job summary

Nebius in the United States is seeking a Staff or Principal Applied AI Researcher to own key parts of our agent-native retrieval and ranking platform. You will drive research directions, ship measurable improvements in production, and collaborate with engineers to scale real-time web data processing for AI systems.

You will design multi-stage retrieval architectures, experiment with embeddings and reranking, and mentor engineers while shaping product and research strategy in a fast-growing cloud

Qualifications

• Experience in applied AI research and building AI systems.
• Proven ability to design retrieval or ranking components for large-scale data.
• Strong understanding of machine learning, systems and deployment implications.

Responsibilities

• Design agent native retrieval systems optimized for machine consumption.
• Build systems where LLMs iteratively plan, query, refine, and reason over results.
• Develop ranking and retrieval approaches for multi-step, agent-driven workflows under real-world constraints.
• Drive applied research and technical direction across retrieval and ranking systems.
• Lead experimentation on modern retrieval approaches (embeddings, hybrid search, reranking) and production deployment.
• Analyse trade-offs across relevance, latency, and cost at scale.
• Work closely with engineering to deploy systems in high-throughput environments.
• Own ambiguous problems end to end and contribute to product and research direction.
• Mentor engineers and help raise the technical bar in the team.

Skills

Applied AI research

Retrieval systems design

Ranking algorithms

ML system engineering

Tools

Embeddings

Hybrid search

Reranking

Job description

Nebius in the United States is seeking a Staff or Principal Applied AI Researcher to own key parts of our agent-native retrieval and ranking platform. You will drive research directions, ship measurable improvements in production, and collaborate with engineers to scale real-time web data processing for AI systems.

You will design multi-stage retrieval architectures, experiment with embeddings and reranking, and mentor engineers while shaping product and research strategy in a fast-growing cloud