Member of Technical Staff, Exceptional Generalist (Remote)
Inferact · Remote · Remote ·
COMPENSATION
€•• – ••k
Listed on the employer's job board (Ashby)
- Fully remote (worldwide)
- vLLM core development
- CUDA & Distributed Systems
- Visa sponsorship available
- Async-first culture
Join Inferact to advance vLLM as the leading AI inference engine. You will solve high-leverage problems end-to-end, working autonomously on low-level optimizations and high-level orchestration. The team consists of vLLM creators focused on making inference faster and cheaper.
What you'll do
- Optimize LLM and diffusion model serving across diverse hardware
- Write low-level kernels to maximize inference engine speed
- Design distributed systems for serving models at global scale
- Build cluster management and deployment automation tools
- Identify and solve critical infrastructure problems independently
What you'll need
- Bachelor's degree or equivalent in computer science or engineering
- Proven ability to drive projects to completion with minimal supervision
- Strong asynchronous communication skills across time zones
- Deep expertise in systems, GPU programming, or distributed systems
- Proficiency in at least two areas: CUDA, Rust/Go/C++, or Python/PyTorch
Nice to have
- Contributions to vLLM or major open-source ML projects
- Experience with NVIDIA, AMD, TPU, or Intel accelerator platforms
- Knowledge of quantization techniques and compiler technologies
- Track record of improving system reliability at scale
- Published technical blogs or impactful side projects
Stack
- vLLM
- CUDA
- Triton
- Rust
- Go
- C++
- Python
- PyTorch
- Kubernetes
How you'll work
- Fully remote position open to candidates worldwide
- Timezone-flexible with overlap required for Pacific Time
- Asynchronous work environment with proactive communication
What you get
- Competitive salary and equity package
- Visa sponsorship available on a case-by-case basis
- Location-appropriate benefits including health coverage