LLM Inference Engineer

Job description

NVIDIA is hiring a LLM Inference Engineer (Full-time) hybrid. This llm engineer role is part of the AI hiring market in Austin (Texas). Ship high-throughput LLM serving stacks for enterprise NIM deployments. Listed compensation: $155k – $220k / year. Stack: TensorRT-LLM, vLLM, Python, GPU.

LLM Engineer profiles are in high demand in Austin: Austin’s tech scene keeps growing with AI product, robotics, and data roles at scale-ups and enterprise R&D labs.…

The team

NVIDIA — AI team

Responsibilities

• Ship production AI features with measurable quality and latency targets
• Partner with product and design on roadmap and customer feedback
• Improve observability, evals, and safe rollout practices

Requirements

• Strong Python or TypeScript fundamentals and 3+ years relevant experience
• Hands-on LLM, ML, or data platform work in production
• Clear written communication and async collaboration

Tech stack

Benefits

Hiring process

1. 1Recruiter screen (30 min)
2. 2Technical interview (60 min)
3. 3Team fit
4. 4Offer

Experience: Mid · 3+ years · Education: BS/MS CS, ML, or equivalent experience

Salary guide — LLM Engineer in Austin →

FAQ — LLM Inference Engineer

What is the salary for LLM Inference Engineer at NVIDIA?

Listed range: $155k – $220k / year (Full-time). Packages often include PTO, remote options, and equity depending on the company.

Where is the LLM Inference Engineer role based?

Austin, TX, Austin (Texas). Work mode: Hybrid.

How do I apply to NVIDIA?

Create a free Ganloss candidate account, then apply in one click. Job reference: EXP-2026-0019. Process: Recruiter screen (30 min) → Technical interview (60 min) → Team fit → Offer.

Is NVIDIA hiring other AI roles?

NVIDIA (Hardware & AI) hires across LLM, ML, data, and AI product. See all openings on the Ganloss company page.

Your profile is sent directly to NVIDIA's hiring team.