Staff Engineer: HPC Distributed DB & In-DB ML

MERCY COLLEGE; Village of Dobbs Ferry (NY); Hybrid; USD 102,000 - 170,000; Full time

Benefits offered by this job

Paid time off

Medical/dental/vision insurance

401(k)

Job summary

Circana is seeking Staff Engineer to design and implement the next-generation, massively parallel processing (MPP) clustered database engine. You will bridge HPC and Big Data systems, crafting low-latency, high-throughput kernels that run on multi-core hardware and large clusters, with in-database ML and advanced vectorized algorithms.

You will lead architecture, optimize for SIMD, RDMA networks, and distributed memory, while collaborating across time zones and mentoring peers.

Qualifications

• 4+ year CS degree; Masters in HPC/Big Data preferred for senior roles
• 6+ years production experience in C++ (C++17/20/23)
• MPI with OpenMP and MapReduce frameworks
• Hardware-aware engineering; SIMD intrinsics
• OS internals, memory barriers, lock-free structures
• DB internals: vectorized operators, LSM-trees, B-trees, buffers

Responsibilities

• Design core architectural choices and roadmap for the distributed kernel
• Write and optimize backend C++ code (C++20/23)
• Architect MPP execution across many nodes using MPI/OpenMP
• Profile and vectorize to maximize cache locality and throughput
• Design ultra-low latency cluster communications (RDMA/DPDK)
• Build native in-database ML framework inside the engine
• Develop vector indices and parallel algorithms for real-time analytics
• Collaborate across time zones and conduct peer reviews
• Engage with cross-functional teams to define platform capabilities
• Investigate and fix performance and scalability challenges

Skills

C++ programming

MPI

OpenMP

Vectorization

Distributed systems

Performance tuning

Debugging

Atomic operations

In-database ML

Education

B.S. in Computer Science

M.S. in HPC

Tools

Valgrind

Purify

Intel Diagnostics

RDMA

DPDK

Job description

Circana is seeking Staff Engineer to design and implement the next-generation, massively parallel processing (MPP) clustered database engine. You will bridge HPC and Big Data systems, crafting low-latency, high-throughput kernels that run on multi-core hardware and large clusters, with in-database ML and advanced vectorized algorithms.

You will lead architecture, optimize for SIMD, RDMA networks, and distributed memory, while collaborating across time zones and mentoring peers.