Founding AI Infrastructure Engineer (+ Equity) at Piris Labs
Jack & Jill · San Francisco, CA · 3 days ago
On-siteInformation Technology$20/hrFull-time
Job Title: Founding AI Infrastructure Engineer
About the role
Piris Labs (YC W26) is a San Francisco startup raising a ~$20M seed round to build the full-stack networking layer for AI inference. Led by engineering veterans from Meta and X alongside an MIT physicist, Piris Labs optimizes large-scale model serving by integrating software orchestration with next-generation GPU and networking architectures.
Responsibilities
- Architect and build a production-grade distributed inference platform featuring multi-node model serving and automated GPU fleet management.
- Develop network-aware request routing and distributed KV-cache management to minimize latency and maximize hardware efficiency.
- Implement high-performance networking protocols and systems using tools like eBPF, RDMA, and NCCL to optimize distributed AI workloads.
Requirements
- Demonstrates exceptional fundamentals in distributed systems, networking, operating systems, and concurrency with a strong builder mentality.
- Possesses deep proficiency in systems languages such as Go, Rust, or C++, and experience with Python for AI orchestration.
- Has a background in high-performance computing, cloud infrastructure, or Kubernetes-based platforms, with a drive to master emerging AI hardware technologies.
Qualifications
- Bachelor’s degree in Computer Science, Electrical Engineering, or a related field.
- At least 5 years of relevant professional experience in AI infrastructure or similar roles.
- Experience with distributed systems, networking, and cloud infrastructure.
- Strong understanding of AI algorithms and machine learning concepts.
Skills
- Systems programming skills (Go, Rust, C++)
- Experience with Python for AI orchestration
- Knowledge of high-performance computing and emerging AI hardware technologies
- Experience with eBPF, RDMA, and NCCL
Benefits
- Equity