Founding Engineer -- AI Inference Stack

At Piris Labs, we are bringing together a world-class software and hardware team to build the next generation of the AI inference stack. Our optimized software solution is built on unique networking hardware that enables AI inference to run at low latency with improved unit economics.

The Role: We are looking for elite systems hackers who want to own the software layer of a new architecture. You will be writing kernels and orchestration logic that outperform existing solutions.

What You Will Do:

• Architect the Stack: Iterate on our software layer that orchestrates inference across heterogenous cluster of compute resources.
• Kernel and Compiler Optimization: Write and optimize high-performance kernels in CUDA, Triton, or custom targets to squeeze every drop of performance from the system.
• The Runtime: Build the low-latency inference server, think a more performant custom version of vLLM or TensorRT-LLM, that manages KV cache at scale without the overhead of traditional PCIe bottlenecks.
• Voice and Agentic Optimization: Solve the unique challenges of instant-on Voice AI, focused on latency, and the high-context demands of coding agents, focused on memory management.

Who You Are:

• Curiosity-driven, with a genuine passion for compute architectures and problem solving
• Systems Obsessed: You have a deep understanding of computer architecture, memory hierarchies, and low-level systems programming in C++, Rust, or CUDA.
• AI Fluent: You understand the guts of transformer architectures and have experience with inference frameworks like vLLM, TensorRT, ONNX, and Kubernetes.
• A First-Principles Thinker: You are not afraid to throw out the standard way of doing things if it means achieving a 10x performance gain.

Why Piris Labs?

• High Stakes, High Growth: We are a small, elite team of builders from Meta and Twitter, trained at Stanford, Harvard, and MIT. No middle management. No alignment meetings. Just engineering.
• Venture Backed: Backed by YC W26 and tier-1 VC firms.
• SF-Centric: We work in person in San Francisco. This is where the density of AI talent is, and we thrive on the high-bandwidth collaboration of a physical lab.
• The Path to Full Time: This internship is a trial run for a founding-level equity stake. We are looking for people to grow with us through our Series A and beyond.