Reducto
Machine Learning Infrastructure Tech Lead
$200K–$325K
San Francisco Office · On-site · Full-time · Posted Nov 3, 2026
- Experience
- 5+ years building production infrastructure, including significant ML systems experience.
About the job
Leads and builds the infrastructure for high-performance machine-learning training and inference, from GPU-level optimization to distributed production systems.
What you'll do
- Own the ML infrastructure technical direction and roadmap; build and maintain the training and inference stack.
- Optimize model serving, distributed systems, and GPU performance for reliability, latency, throughput, observability, and cost.
- Develop benchmarks and tooling, guide architecture and capacity planning, and provide hands-on technical leadership and mentorship.
What they ask for
- 5+ years of experience building production infrastructure, including significant ML systems experience.
- Strong Python and systems-engineering skills.
- Understanding of performance characteristics of modern GPU training or inference workloads.
- Comfort with Kubernetes and distributed training or serving frameworks.
Nice to have
- Optimized or implemented CUDA, Triton, or custom model-serving kernels.
- Contributed to frameworks such as vLLM, SGLang, PyTorch, TensorRT-LLM, or Ray.
Pay
$200K – $325K (base salary)
Tools
Python, Kubernetes, CUDA, Triton, vLLM, SGLang, PyTorch, TensorRT-LLM
AI focus
Builds and optimizes infrastructure for ML model training and inference, including distributed GPU workloads and production model serving.
Model-written summary · the original posting is authoritative