AI Optimization Engineer | GPU HPC Onsite in Jersey City

Simple Solutions; Jersey City (NJ); On-site; USD 150,000 - 190,000; Full time

Job summary

Zohorecruit seeks an AI Optimization Engineer to design and optimize AI/ML workloads on GPU-based HPC clusters in Jersey City, NJ. You will deploy large language models in scalable production environments and implement model optimization techniques.

The role requires hands-on ML/DL with Python, SLURM, Docker/Kubernetes, and modern AI tooling. Onsite work in Jersey City, collaboration with AI, infra, and DevOps teams.

Qualifications

• Hands-on Python-based ML/DL experience with TensorFlow, PyTorch or Keras.
• Experience with GPU HPC clusters and SLURM workload orchestration.
• Familiarity with deploying LLMs and AI inference pipelines.
• Proficiency with containerization and DevOps tools.

Responsibilities

• Design and optimize AI/ML workloads on GPU-based HPC clusters.
• Deploy and manage LLMs in scalable production environments.
• Implement model optimization techniques (pruning, quantization, distillation).
• Develop automated SLURM workflows with REST/Flask APIs.
• Monitor performance with Prometheus and Grafana.
• Optimize inference pipelines with Triton Inference Server/ TRTLLM.
• Collaborate with infra/ML teams to improve scalability.

Skills

Python-based ML

Deep learning

NLP

Transformers

Generative AI

Model optimization

Tools

Docker

Kubernetes

MLFlow

Terraform

Jenkins

GitHub

HuggingFace

SLURM

Triton Inference Server

TRTLLM

Flask

Linux administration

Enroot

Pyxis

Podman

Plotly

Seaborn

Matplotlib

Job description

Zohorecruit seeks an AI Optimization Engineer to design and optimize AI/ML workloads on GPU-based HPC clusters in Jersey City, NJ. You will deploy large language models in scalable production environments and implement model optimization techniques.

The role requires hands-on ML/DL with Python, SLURM, Docker/Kubernetes, and modern AI tooling. Onsite work in Jersey City, collaboration with AI, infra, and DevOps teams.