INFERENCE ENGINEER

The role

You will build and operate production inference systems that serve large models. The role involves serving infrastructure, runtime optimization, and production infrastructure to make research work fast and reliable.

What you will do

• Build, operate, and harden production inference systems serving large models at high throughput
• Own performance characteristics including throughput, latency, cost-per-token, and reliability
• Profile real workloads to identify bottlenecks and ship fixes
• Implement and integrate inference optimizations from the research team
• Design observability into the inference layer
• Run capacity planning, autoscaling, and load testing
• Diagnose and resolve production incidents and write postmortems

Required qualifications

• Senior ML systems engineer with 3+ years building production-grade, large-scale serving infrastructure
• Strong distributed systems experience
• Experience being on-call for systems that matter
• Performance profiling and optimization fluency
• Experience with GPU-accelerated inference at scale (multi-GPU, multi-node, batched and streaming workloads)
• Fluent Python
• Comfortable reading and writing systems-level code in at least one of the following languages: C++, CUDA, ROCm or Triton
• Track record of shipping production infrastructure
• Good written communication

Nice to have

• Experience with AMD GPUs
• Surfaces serving millions of requests across diverse workloads
• Open-source contributions to inference / serving frameworks
• Experience with mixed cloud and on-premises deployments
• Familiarity with hardware-aware optimization (memory hierarchy, NCCL/RDMA, NUMA)
• Background in compilers, runtimes, or accelerator software stacks

About the company

makermaker.ai is a small, well-funded team building autonomous research agents for recursive self-improvement.