Software Engineer (AI Infrastructure)

TL;DR

Software Engineer (AI Infrastructure): Building the orchestration layer for large-scale AI compute by partitioning, scheduling, optimizing, and executing AI workloads across heterogeneous hardware with an accent on compiler/runtime systems and production inference performance. Focus on MLIR/compiler optimizations, runtime execution planning, scheduling and memory movement efficiency, and latency-focused serving architectures.

Location: San Francisco, CA (Onsite)

Salary: $150,000-$400,000 Base + Equity

Company

hirify.global is an AI infrastructure company building software to orchestrate AI workloads across diverse compute hardware.

What you will do

• Design and implement compiler optimizations and IR transformations for AI workloads using MLIR.
• Build runtime systems and execution planning to improve how AI workloads run in production.
• Develop scheduling and workload partitioning across heterogeneous hardware architectures.
• Optimize memory movement, kernel orchestration, and execution efficiency for inference workloads.
• Improve AI inference serving with latency optimization, including speculative decoding and next-generation serving architectures.
• Profile and debug performance bottlenecks across the AI software stack.

Requirements

• Strong systems programming and performance engineering fundamentals.
• Experience building compiler systems, runtime systems, or execution infrastructure.
• Experience implementing compiler passes, IR transformations, lowering, or code generation systems.
• Strong understanding of memory systems, scheduling, and hardware performance.
• Strong C++ and/or Python engineering skills.
• Experience working on performance-critical systems.

Nice to have

• Experience optimizing large-scale inference workloads.
• Experience with GPUs, AI accelerators, or heterogeneous compute systems.
• Familiarity with kernel dispatch, launch APIs, or memory allocators.
• Experience with distributed systems and serving infrastructure.
• Experience profiling and debugging production performance bottlenecks.

Culture & Benefits

• Onsite role in San Francisco, CA.
• Base salary plus equity.
• Work on non-traditional compiler problems spanning compilers, runtime systems, serving infrastructure, and execution optimization.

Hiring process

• Initial conversation to discuss compilers, runtime systems, and AI workload execution challenges.