Senior AI Engineer: NVIDIA LLM Inference on GPU

FullStack; Toronto; Hybrid; CAD 120,000 - 180,000; Full time

Benefits offered by this job

Competitive pay

Career growth

Education opportunities

Job summary

FullStack is seeking a Senior AI Engineer to join our talent network and work with U.S. clients on flexible, project-based development. You will integrate directly into client teams and contribute to production-grade AI inference on GPU infrastructure.

Requirements include 5+ years in AI/ML engineering, advanced English, a four-year degree, and hands-on NVIDIA stack experience (NIM, NeMo, TensorRT-LLM). Hybrid work with international collaboration is expected.

Qualifications

• 5+ years of professional experience in AI/ML engineering or related fields.
• Advanced English is required.
• Bachelor's degree in a relevant field.
• Strong hands-on experience with NVIDIA's AI inference stack (NIM, NeMo, Guardrails, TensorRT-LLM, Triton).
• Experience deploying and self-hosting LLMs in production on GPU infrastructure.
• Experience with GPU clusters and Kubernetes-based environments.
• Understanding of LLMs, inference optimization, and model serving.
• Experience building private on-prem AI inference platforms.
• Ability to implement guardrails for production LLM apps.

Responsibilities

• Integrate into client teams and collaborate with designers and engineers daily.
• Help deploy and scale AI inference workloads on GPU infrastructure.
• Contribute to libraries and improve production-grade pipelines.

Skills

AI/ML engineering

NVIDIA GPU stack

Kubernetes

LLM inference

Agile/Scrum

English proficiency

Problem solving

Ownership

Education

Bachelor's degree

Tools

NIM

NeMo

NeMo Guardrails

TensorRT-LLM

Triton Inference Server

GPU Operator

Job description

FullStack is seeking a Senior AI Engineer to join our talent network and work with U.S. clients on flexible, project-based development. You will integrate directly into client teams and contribute to production-grade AI inference on GPU infrastructure.

Requirements include 5+ years in AI/ML engineering, advanced English, a four-year degree, and hands-on NVIDIA stack experience (NIM, NeMo, TensorRT-LLM). Hybrid work with international collaboration is expected.