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
- For scenarios such as AI data centers and cloud resource scheduling, understand business requirements, formulate mathematical models, and design and develop efficient algorithms, heuristic algorithms, and meta-heuristic algorithms for optimization problems. -Explore AI for OR by integrating LLM, RL and Agent technologies into the operations research optimization pipeline, including but not limited to: Natural language-based decision engine interfaces & Enhancing the interpretability of optimization results
Requirements
Minimum Qualifications:
- Ph.D. degree with strong research achievements, such as multiple first-author papers at conferences (CCF-A) in the areas of Data, Systems, or AI.
- Solid foundation in operations research theory, with expertise in areas such as linear programming, integer programming, and combinatorial optimization. - Proficient with at least one mainstream commercial or open-source solver (e.g., Gurobi, CPLEX, CP-SAT). Familiar with commonly used (meta-)heuristic algorithms (e.g., genetic algorithms, simulated annealing) and experienced in real-world deployment.
- Strong engineering and coding skills, proficient in at least one programming language such as Python, C++, or Java, with solid knowledge of common data structures and algorithms.
- Excellent logical thinking and business abstraction skills, capable of translating ambiguous business requirements into clear technical solutions.
- Strong communication, teamwork, and collaboration abilities.
Preferred Qualifications:
- Domain knowledge of datacenter hardware supply chain operations or the underlying implementation of cloud computing products.
- Familiarity with LLMs, reinforcement learning, and Agent frameworks such as LangGraph. Experience with prompt engineering optimization and Agent development. Strong interest and insight in combining traditional operations research optimization with generative AI.