About the Team We are the Infrastructure System Lab — a hybrid research and engineering group building the next-generation AI-native data infrastructure. Our work sits at the intersection of databases, large-scale systems, and AI. We drive innovation across:
- Next-generation databases: We build VectorDBs and multi-modal AI-native databases designed to support large-scale retrieval and reasoning workloads.
- AI for Infra: We leverage machine learning to build intelligent algorithms for infrastructure optimization, tuning, and observability.
- LLM Copilot: We develop LLM-based tooling like NL2SQL, NL2Chart.
- High-performance cache systems: We develop a multi-engine key-value store optimized for distributed storage workloads. We're also building KV caches for LLM inference at scale. This is a highly collaborative team where researchers and engineers work side-by-side to bring innovations from paper to production. We publish, prototype, and build robust systems deployed across key products used by millions.
About the Role We are seeking a highly motivated and technically strong Research Scientist with a PhD in Computer Science, Database, Information Retrieval, or a related field to join our team. You will work on designing and optimizing state-of-the-art vector indexing algorithms to power large-scale similarity search, filtered search, and hybrid retrieval use cases. Your work will directly contribute to the next-generation vector database infrastructure that supports real-time and offline retrieval across billions or even trillions of high-dimensional vectors.
Why Join Us
- Work on problems at the frontier of AI x systems with huge practical impact.
- Collaborate with a world-class team of researchers and engineers.
- Opportunity to publish, attend conferences, and contribute to open-source.
- Competitive compensation, generous research support, and a culture of innovation.
Responsibilities
- Research and develop new algorithms for approximate nearest neighbor (ANN) search, especially for filtered, hybrid, or disk-based scenarios.
- Optimize existing algorithms for scalability, low latency, memory footprint, and hybrid search support.
- Collaborate with engineering teams to prototype, benchmark, and productionize indexing solutions.
- Contribute to academic publications, open-source libraries, or internal technical documentation.
- Stay current with research trends in vector search, retrieval systems, retrieval-augmented generation (RAG), large language models (LLMs), and related areas.
Requirements
Minimum Qualifications
- PhD in Computer Science, Applied Mathematics, Electrical Engineering, or a related technical field.
- Strong publication record in accredited venues (e.g., SIGMOD, VLDB, SIGIR, NeurIPS, ICML, etc.) related to vector search, indexing, IR, or ML.
- Deep understanding of ANN algorithms, quantization, graph-based indexes, and partition-based indexes.
- Strong system-level thinking: ability to profile, benchmark, and optimize performance across CPU, memory, and storage layers.
- Proficiency in C++ and/or Python, with experience in implementing and benchmarking algorithms.
Preferred Qualifications
- Experience building or contributing to vector databases or retrieval engines in production.
- Familiarity with frameworks like FAISS, ScaNN, HNSWLib, or DiskANN.
- Understanding of distributed systems and/or GPU-accelerated search.
- Experience with hybrid search (dense + sparse), multi-modal retrieval, or retrieval for LLMs.
- Passion for bridging theory and practice in production-scale systems.