ZR_2880_JOB

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

Jersey City, United States | Posted on 04/14/2026

Job Description Summary – AI Optimization Engineer (Onsite, Jersey City, NJ)

We are seeking an experienced AI Optimization Engineer to support large-scale AI/ML and Generative AI workloads for an enterprise environment. This role focuses on optimizing, deploying, and managing machine learning and large language models (LLMs) on GPU-accelerated HPC infrastructure. The ideal candidate will have strong experience in Python-based machine learning, deep learning frameworks, model optimization techniques, and scalable AI infrastructure.

The engineer will work closely with AI, infrastructure, and DevOps teams to design efficient model training and inference pipelines, implement SLURM-based workload orchestration, and deploy containerized ML solutions in production environments. Responsibilities include optimizing model performance using techniques such as pruning, quantization, and knowledge distillation, managing inference workflows using Triton Inference Server, and monitoring system performance using Prometheus and Grafana.

This role requires hands-on experience with HPC environments, GPU clusters, containerization technologies, and Linux system administration, along with strong knowledge of machine learning algorithms, deep learning architectures, and modern AI development tools. Experience with cloud platforms, vector embedding, and enterprise-scale AI deployments is highly preferred.

Core Responsibilities

Design and optimize AI/ML workloads on GPU-based HPC clusters.

Deploy and manage large language models (LLMs) in scalable production environments.

Implement model optimization techniques including pruning, quantization, and knowledge distillation.

Develop and manage automated job scheduling using SLURM with REST and Flask APIs.

Monitor system performance using Prometheus and Grafana.

Optimize inference pipelines using Triton Inference Server and TRTLLM.

Conduct exploratory data analysis and model performance evaluation.

Collaborate with infrastructure and ML teams to improve scalability and efficiency.

Skills Required

The AI Optimization Engineer must have strong experience in Python-based machine learning and deep learning, including NumPy, scikit-learn, TensorFlow, PyTorch, and Keras, with hands-on knowledge of supervised and unsupervised learning, neural networks, transformer-based models, NLP, CNNs, and Generative AI concepts. The role requires expertise in AI infrastructure and optimization, including HPC environments, GPU clusters, SLURM workload management, Triton Inference Server, TRTLLM, and model optimization techniques such as pruning, quantization, and distillation for scalable LLM deployment.

Candidates should also have experience with DevOps and deployment tools such as Docker, Kubernetes, MLFlow, Terraform, Jenkins, GitHub, and HuggingFace, along with strong skills in performance monitoring using Prometheus and Grafana. Additional requirements include Flask API development, Linux administration (RHEL/CentOS), container runtimes like Enroot, Pyxis, and Podman, and experience with data analysis and visualization tools such as Plotly, Seaborn, and Matplotlib.