Tech Lead, AI Inference & High-Performance Systems

Visa Hunt; United States; On-site; USD 180,000 - 240,000; Full time

Benefits offered by this job

Medical, Dental, Vision

401(K)

Flexible Time Off

Job summary

WEKA is seeking a Tech Lead to steer its AI Inference team, balancing hands-on engineering with strong people leadership. You will grow a squad of 3 engineers, drive end-to-end inference architecture from NVMe data paths to vLLM/LMCache serving stacks, and set high standards for performance and reliability.

You will mentor engineers, shape the team culture, and stay at the frontier of inference frameworks while guiding when to adopt or build new solutions.

Qualifications

• 5+ years of professional software engineering leadership.
• Deep AI inference background with production systems experience.
• Strong Python/C++ skills and high-performance computing exposure.

Responsibilities

• Lead and grow a 3-engineer squad; balance hands-on work with people leadership.
• Own AMG's core inference infrastructure from data paths to serving stack.
• Set direction, unblock the team and drive high-throughput, low-latency systems.
• Mentor engineers, conduct regular 1:1s, and foster ownership and excellence.
• Stay current with the inference ecosystem and guide tool adoption decisions.

Tools

Python

C++

CUDA

vLLM

LMCache

Kubernetes

GDS

RDMA

NVMe

GPUDirect Storage

Job description

WEKA is seeking a Tech Lead to steer its AI Inference team, balancing hands-on engineering with strong people leadership. You will grow a squad of 3 engineers, drive end-to-end inference architecture from NVMe data paths to vLLM/LMCache serving stacks, and set high standards for performance and reliability.

You will mentor engineers, shape the team culture, and stay at the frontier of inference frameworks while guiding when to adopt or build new solutions.