NVIDIA AI Enterprise Engineer / Architect / MLOps

NVIDIA AI Enterprise Engineer / Architect

OnTarget Labs is a leading international software product development company.
We create next generation of world class product lines.

The company is looking for NVIDIA AI Enterprise Engineers and Architects to join our innovative product team as a full-time member working REMOTELY.
Lots of opportunities for professional growth and business trips abroad are offered.
Join our friendly team of IT professionals now!

Role description

You will take AI from pilot to production on NVIDIA AI Enterprise (NVAIE), NVIDIA's end-to-end, cloud-native software suite for building, deploying and managing production AI.

You will build and run GPU-accelerated AI platforms on-prem, in VMware and in the cloud, and deliver generative AI use cases across industries.

• Engineer: builds, deploys and operates the NVAIE platform and AI workloads.
• Architect: Also owns the target design, technical decisions and guidance for the client's engineers.

Responsibilities

• Build: deploy and maintain NVAIE on NVIDIA-Certified systems, VMware vSphere / VMware Private AI Foundation, Kubernetes or AWS/Azure/GCP.
• Ship GenAI: stand up NIM microservices, RAG and agent workflows from NVIDIA Blueprints, and fine-tune or guardrail models with NeMo.
• Operate: own GPU orchestration, monitoring, security, upgrades and MLOps so workloads scale across nodes and stay supported in production.
• Transfer knowledge: document the platform and coach client engineers so they can run it themselves.

Tech stack

• Inference & GenAI: NVIDIA NIM, NeMo, Triton Inference Server, TensorRT-LLM
• Data science: RAPIDS, PyTorch, TensorFlow
• Orchestration: NVIDIA Run:ai, GPU Operator, Kubernetes / Helm, NGC catalog
• Infrastructure: NVIDIA-Certified systems, VMware vSphere & Private AI Foundation, vGPU, AWS / Azure / GCP

Requirements

• Bachelor’s degree in Information Systems, Computer Science, or a related field
• Excellent verbal and written communication skills in English
• Engineer: 5+ years in ML engineering, MLOps or AI infrastructure, including 2+ years on GPU workloads.
• Architect: 8+ years, including designing enterprise AI or cloud platforms end to end.
• Hands-on production experience with NVAIE components, especially NIM, NeMo, Triton.
• Strong Kubernetes, containers and Linux;
• Comfort with VMware vSphere and GPU virtualization.
• Delivered at least one GenAI/LLM solution (RAG, fine-tuning or agents) into enterprise production.
• Python fluency
• Infrastructure-as-code (Terraform, Ansible, Helm).

We offer

• Competitive compensation to be defined upon the interview results
• Full time REMOTE WORK