Distributed Systems Engineer

Cadence Design Systems•Vancouver, BC

67d•Onsite

About The Position

We're building a next-generation distributed transistor-level electromigration and IR drop analysis tool. Our team has strong expertise in numerical solvers and circuit simulation algorithms. We're looking for a motivated distributed systems engineer to help build the scalable data processing infrastructure for handling massive circuit designs across distributed computing resources.

Requirements

3+ years building distributed systems with Python
Experience with distributed computing frameworks (Dask, Spark, Ray, or Celery)
Understanding of distributed computing patterns, data locality, and fault tolerance
Experience with high-performance data formats (HDF5, Parquet, Arrow, or similar columnar formats)
Familiarity with data partitioning strategies and streaming patterns
Some exposure to Python/C++ interop (pybind11, nanobind)
Strong Python, C++ programming skills with production code experience
Comfortable working in large codebases and collaborative development environments
Understanding of software engineering best practices (testing, code review)

Nice To Haves

Background in EDA, VLSI, semiconductor design, or computational engineering
Experience with scientific/engineering data visualization
HPC experience with job schedulers (Slurm, PBS, LSF)
GPU acceleration knowledge
Familiarity with modern tools (Go, Plotly, Bokeh, Holoviews, Datashader)
Open-source distributed computing or other contributions
Experience with cloud platforms (AWS, GCP, Azure)

Responsibilities

Build ingestion pipelines for large-scale netlists and simulation data
Implement high-performance I/O for multi-TB circuit databases
Develop serialization/deserialization layers bridging Python and C++ components
Design streaming interfaces for distributed solver results
Implement task distribution with fault-tolerant scheduling for long-running simulations
Develop resource management and load balancing across compute clusters
Build monitoring and observability for distributed workflows
Optimize task granularity and dependency management
Develop scalable visualization for multi-dimensional TB-scale simulation results
Implement interactive data exploration with optimization techniques (downsampling, LOD, progressive rendering)