5 months ago
Base Salary
$175k - $250k/yr
Responsibilities
- Research, evaluate, and implement vector indexing and retrieval algorithms for Milvus, Zilliz Cloud, and Vector Lakebase.
- Build and optimize high-performance indexing components covering query paths, preprocessing, quantization, compression, memory layout, and CPU/GPU acceleration.
- Optimize retrieval latency, throughput, recall, memory usage, index build time, and cost efficiency.
- Design benchmarks and evaluation frameworks using real-scale data, query patterns, and AI workloads.
- Debug performance issues involving algorithm implementation, CPU/GPU execution, SIMD/vectorization, memory access, concurrency, and I/O.
- Convert research prototypes into maintainable, testable, and evolvable production capabilities.
- Use AI tools for paper analysis, prototyping, implementation, testing, benchmarking, documentation, and performance analysis.
Requirements
- At least 3 years of experience in vector search, ANN algorithms, search systems, high-performance computing, or performance-critical systems.
- Bachelor's degree in Computer Science, Software Engineering, or a related field, or equivalent practical experience.
- Strong C++ or Rust programming ability and solid engineering fundamentals.
- Experience with vector similarity search, ANN algorithms, index structures, quantization, compression, reranking, or high-performance retrieval systems is preferred.
- Strong interest in research-driven engineering, including reading papers, evaluating tradeoffs, building prototypes, and productionizing ideas.
- Performance optimization and systematic debugging experience, particularly with CPU/GPU execution, SIMD, memory layout, concurrency, I/O, or large-scale data processing, is preferred.
- Interest in using AI tools to improve research, coding, testing, benchmarking, documentation, and performance analysis.
Benefits
- Competitive compensation including cash and equity, regular bonuses, and equity refresh opportunities.
- Medical, dental, and vision insurance.
- Paid time off including vacation, sick leave, and global reset/wellbeing days.
- 401(k) and regional retirement plans.
About Zilliz
Zilliz develops vector database software for AI applications, including the open-source Milvus project and a managed cloud service with enterprise features. Founded in 2017 and headquartered in Redwood City, California, the privately held company was started by the engineers behind Milvus and sells subscriptions, cloud usage, and support to organizations building similarity search, retrieval-augmented generation, and other unstructured-data workloads.