AI Inference Engineer — QVAC

Company: Tether (tether.io)

Job Category: AI / Machine Learning Engineering

Contract Type: Full-Time | Permanent

Location: 100% Remote — Worldwide

Salary: $100,000 – $500,000+ (range per Web3 Jobs data for Tether roles)

Posted: May 6, 2026 (Active)

About the Company: Tether envisions a world where technology enables financial freedom, educational empowerment, energy sustainability, and data sovereignty. All of their roles are fully remote, worldwide. Tether is the issuer of USDT, the world's largest stablecoin by market cap, and is expanding into AI infrastructure under its QVAC division.

Job Description: As AI Inference Engineer on the QVAC team, you will develop and optimize AI inference systems at scale. You'll work on low-latency model deployment, quantization, hardware acceleration, and edge inference pipelines—contributing to Tether's mission of on-device and decentralized AI.

Skills Required:

• LLM inference optimization (quantization, ONNX, TensorRT, etc.)
• Python and C++
• GPU architecture knowledge (CUDA, ROCm)
• Experience with model deployment at scale
• Distributed systems and edge AI

Requirements:

• 5+ years of ML engineering experience
• Hands-on inference optimization background
• Remote-capable with strong async communication
• Worldwide eligibility — no location restriction

Application Link: https://careers.tether.io/o/ai-inference-engineer-qvac-100-remote-worldwide?source=Hackernews

Closing Date: Open until filled