Inference Engineering, Co-op
Core
Build systems for fast, efficient, and reliable AI model inference at scale, including runtimes, kernels, and distributed serving.
Role type
Co-op Inference Engineer (Systems)
Builds
Open source vLLM inference engine and production-grade tooling for AI workloads (via careerplan.io/jobs/2b6032f9-12a5-4083-b5e6-4bec5376cbaa-inference-engineering-co-op-at-inferact)
Domain
AI Infrastructure / High-Performance Computing / Distributed Systems
Deliverable
production ML models
Required skills
Python, C++, Rust, Go, CUDA, Triton, Kubernetes, distributed systems, GPU programming
Preferred skills
ML inference systems, compilers, high-performance computing, profiling, multi-GPU/multi-node systems
Technologies
vLLM, PyTorch, NCCL, DeepEP, ROCm, JAX, XLA, Kubernetes, Terraform
Responsibilities
Implement inference techniques from research papers, optimize kernels for GPU/TPU/AMD accelerators, build distributed serving data planes, develop cloud orchestration platforms
Seniority
Co-op / Intern
