Hands-On Tech Lead for Large-Scale Inference

Luma AI; United States; Remote; USD 180,000 - 320,000; Full time

Job summary

Luma AI seeks a hands-on Tech Lead Manager to own the inference serving stack, including routing, scheduling, and fleet-wide orchestration across thousands of GPUs and multiple clouds. The role demands staying hands-on while hiring, growing the team, and steering technical direction.

Expected to lead the team through the first 90 days by diagnosing the stack, shipping a meaningful platform improvement, and scaling reliability and cost efficiency for production multi-cluster deployments.

Qualifications

• 8+ years in large-scale distributed systems or ML infrastructure.

Responsibilities

• Own and troubleshoot the serving stack latency, reliability, and cost.
• Lead, grow, and coach inference engineering team including on-call and postmortems.
• Set technical roadmap for serving engines, routing, scheduling, and autoscaling.
• Own platform SLOs and budget, monitor GPU utilization and cost per generation.
• Collaborate with research to ship architectures to production and integrate with online eval loops.

Skills

Distributed systems

ML infrastructure

LLM serving

Python

PyTorch

Kubernetes

Scheduling

GPU clusters

Cost optimization

Incident response

Tools

vLLM

SGLang

TensorRT-LLM

KV-cache management

Job description

Luma AI seeks a hands-on Tech Lead Manager to own the inference serving stack, including routing, scheduling, and fleet-wide orchestration across thousands of GPUs and multiple clouds. The role demands staying hands-on while hiring, growing the team, and steering technical direction.

Expected to lead the team through the first 90 days by diagnosing the stack, shipping a meaningful platform improvement, and scaling reliability and cost efficiency for production multi-cluster deployments.