Tech Stack

Description

You will lead applied research at the intersection of search, retrieval, and LLM-based systems, building an agent-native search platform that serves as the web access layer for AI systems. The focus is on solving retrieval and search problems under new access patterns and scale, with research tightly coupled to large-scale production deployment.

Requirements

• 8+ years of experience in applied AI, ML, or software engineering
• Proven track record of shipping ML/AI systems into production at scale
• Deep experience in search, retrieval, ranking, recommendation systems, or assistants
• Strong understanding of modern deep learning (transformers, embeddings, ranking models)
• Strong programming skills in Python and at least one of Go, C++, or similar

Responsibilities

• Drive applied research across retrieval, ranking, and agent-centric search systems
• Design and evolve multi-stage retrieval systems including query understanding, rewriting, reranking, iterative retrieval
• Develop methods for grounding LLMs in real-time web data at scale
• Define evaluation frameworks and quality metrics for agent-native workloads
• Lead experimentation on modern retrieval approaches (hybrid search, embeddings, cross-encoders)