Senior Platform / Systems Engineer

Data Science UA is a service company with deep expertise in AI and Data Science. Our story started in 2016 with the first Data Science UA Conference in Kyiv, and since then, we’ve built one of the largest AI communities in Europe.

About the client:
The company is on a mission to make the world’s industrial environments safer with technology solutions and to drive a paradigm shift in safety from reactive to proactive approaches to reduce the risk of industrial accidents. The team in Ukraine is developing the future of industrial safety based on machine learning, computer vision, and IoT.

About the role:
We are looking for a Senior Platform / Systems Engineer to build high-throughput data pipelines and shared memory infrastructure using Python (3.11+), ZeroMQ, and CUDA. You will focus on low-latency IPC, memory management, and scaling our processor-wrapper ecosystem for real-time systems.

Responsibilities: 
- Pipeline Engine (Python DAG orchestrator)
- Shared memory pools (C library + Python/Go bindings)
- ZeroMQ IPC layer, FlatBuffers metadata serialization
- ProcessorWrapper infrastructure.

Must-have:
- Python 3.11+ at a senior level — deep understanding of concurrency, multiprocessing, GIL behavior, and memory management
- CUDA basics — IPC handle management, stream synchronization, CPU↔GPU transfers (not model training, but GPU memory management)
- Experience in Docker/container environment
- Linux systems programming — /dev/shm, process isolation, file descriptors, signals

Nice to have: 
- C/C++ for the shared memory manager (POSIX shm, lock-free Treiber stacks, atomic CAS operations, pybind11/ctypes bindings)
- ZeroMQ — PUSH/PULL and PUB/SUB patterns
- FlatBuffers — schema design and zero-copy access patterns
- Docker/container networking, OpenTelemetry instrumentation.
- OpenCV/CV-CUDA - image processing processors use OpenCV for CPU frames and CV-CUDA (nvcv). For GPU frames
- Tensor RT - Future work includes auto exporting YOLO models to Tensor RT engine format to achieve 2-3x inference speedup
- Connect RPC (Buf ecosystem)
- Experience building developer tooling for ML pipelines, robotics platforms, or real time video systems is a strong plus.

We offer:
- Good compensation;
- Benefit package;
- Strong team and career growth;
- Challenges every day!