Software Engineer, TT-Distributed (AI)

TL;DR

Software Engineer, TT-Distributed (AI): Developing and optimizing distributed software systems that power high-performance AI and HPC clusters with an accent on inter-node communication and scalable architectures. Focus on designing distributed APIs for data-parallel and tensor-parallel workloads and scaling programming models across multiple compute nodes.

Location: Hybrid; must be based in Santa Clara (CA), Austin (TX), or Toronto (ON)

Salary: $100k - $500k (including base and variable compensation)

Company

hirify.global is leading the industry on cutting-edge AI technology, revolutionizing performance expectations, ease of use, and cost efficiency.

What you will do

• Architect and optimize distributed software systems that coordinate computation across clusters of AI accelerators and CPUs.
• Design and build distributed APIs enabling data-parallel and tensor-parallel AI workloads.
• Scale programming models across multiple hosts and compute nodes using MPI-based technologies and frameworks.
• Develop robust systems using IPC, inter-node sockets, and distributed communication primitives.
• Build and maintain testing, debugging, profiling, and monitoring tools for large-scale distributed workloads.

Requirements

• Strong proficiency in C or C++ with solid foundations in systems programming and operating systems.
• Deep understanding of distributed systems principles, including IPC, socket programming, and cluster resource coordination.
• Ability to reason about scalability, fault tolerance, and performance in multi-node environments.
• First-principles thinking and motivation to become a technical expert in large-scale AI infrastructure.
• Must be eligible to access U.S. export-controlled technology (compliance with EAR).

Culture & Benefits

• Highly competitive compensation package and comprehensive benefits.
• Opportunity to work with next-generation RISC-V CPU and AI platform technology.
• Collaborative environment focused on solving hard technical problems and challenging conventional designs.
• Direct exposure to the architecture of large-scale distributed inference and training systems.