Founding Engineer, AI Infrastructure

Piris Labs; San Francisco (CA); On-site; USD 100,000 - 200,000; Full time

Benefits offered by this job

Equity

401(k)

Health insurance

Direct impact on product decisions

Job summary

Piris Labs is building the next generation of AI inference infrastructure. We are seeking a Founding AI Infrastructure Engineer to architect and build our inference platform from first principles.

This role spans the entire stack—from control plane orchestration to distributed serving systems, networking, scheduling, observability, and performance optimization. As an early engineer, you will have enormous influence over our architecture, engineering culture, hiring strategy, and product

Qualifications

• Strong foundations in distributed systems, networking, OS, databases, concurrency, and design.
• Proven ability to build systems from scratch and own high-impact problems.
• Proficiency in Go, Rust, C++, or Python.
• Experience with Kubernetes, Linux, containers, service meshes, cloud infra, and automation.

Responsibilities

• Architect and build inference platform from ground up across control plane to distributed serving.
• Work on multi-node model serving, intelligent global request routing, scheduling, observability, and performance optimization.
• Own the engineering foundation and contribute to hiring strategy and product direction.

Skills

Distributed systems

Networking

Operating systems

Databases

Concurrency

Systems design

Go

Rust

C++

Python

Kubernetes

Linux

Containers

Service meshes

Cloud infrastructure

Infrastructure automation

Tools

Kubernetes

Envoy

eBPF

OpenTelemetry

NCCL

RDMA

InfiniBand

TensorRT-LLM

Job description

We are building the next generation of AI inference infrastructure. Our mission is to make large-scale model serving dramatically faster, more efficient, and more reliable by tightly integrating software orchestration with next-generation GPU and networking architectures. We believe the future of AI infrastructure will be defined not just by larger models, but by how effectively those models are distributed across nodes, networks, regions, and heterogeneous hardware. We're assembling a small, high-caliber engineering team to build that future from the ground up.

The Role

We are looking for a Founding AI Infrastructure Engineer to help architect and build our inference platform from first principles. This is not a traditional backend role. You will work across the entire inference stack, from control plane orchestration to distributed serving systems, networking, scheduling, observability, and performance optimization. You will help solve some of the hardest problems in AI infrastructure. As one of the first engineers, you will have enormous influence over our architecture, engineering culture, hiring strategy, and product direction. This role is designed for builders who want to create foundational technology, not maintain existing systems.

What You Will Work On

• Multi-node inference
• Network-aware request routing
• Distributed KV-cache management
• Scale-to-zero and instant scale-up
• Cluster scheduling and placement
• High-performance networking
• Resource isolation and multi-tenancy
• Large-scale observability and reliability

What We're Looking For

Strong Technical Foundations: exceptional fundamentals in distributed systems, networking, operating systems, databases, concurrency, and systems design. Builder Mentality: you enjoy building new systems from scratch and taking ownership of ambiguous, high-impact problems. Programming Excellence: strong experience in one or more of Go, Rust, C++, or Python. Infrastructure Experience: experience with Kubernetes, Linux systems, containers, service meshes, cloud infrastructure, and infrastructure automation. High Learning Velocity: we care more about your ability to learn and execute than your years of experience.

Particularly Exciting Backgrounds

AI infrastructure companies, distributed databases, high-performance networking, cloud infrastructure platforms, GPU systems, HPC environments, Kubernetes platforms, and large-scale backend systems. Experience with technologies such as Kubernetes, Envoy, eBPF, OpenTelemetry, vLLM, SGLang, TensorRT-LLM, NCCL, RDMA, and InfiniBand is a strong plus, but not required.

What Success Looks Like

Within your first year, you will help build a production-grade distributed inference platform, multi-node model serving capabilities, intelligent global request routing, automated GPU fleet management, and the foundation of our engineering organization.

Why Join

• Competitive salary and benefits
• Direct access to customers and product decisions
• Significant technical ownership from day one
• Opportunity to build category-defining AI infrastructure
• Work alongside engineers solving some of the most challenging systems problems in modern computing

Compensation: $100,000–$200,000 depending on experience, plus equity, 401(k), health insurance, and benefits [e-mail]