AI Optimization Engineer

Job Title: AI Optimization Engineer

Location: Jersey City ,NJ 3 Days onsite

Duration: Long Term

Position Overview:

The AI Optimization Engineer will support advanced artificial intelligence and machine learning initiatives with a focus on performance optimization, scalable infrastructure, and production deployment. This is a six month contract role requiring onsite presence three days per week in Jersey City, New Jersey. The role supports enterprise AI and ML workloads, including large language models, GPU accelerated environments, and high performance computing platforms.

Responsibilities:

· Design, optimize, and deploy machine learning and deep learning models for production environments

· Support scalable infrastructure for large language models and AI workloads

· Design and manage GPU accelerated clusters for large scale AI and machine learning use cases

· Develop and maintain automated and secure job scheduling using SLURM with REST and Flask APIs

· Deploy models using container based and microservice oriented architectures

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

· Configure and optimize Triton Inference Server, including model serving and performance tuning

· Build secure Flask based APIs to support inference and orchestration

· Monitor and analyze system and model performance using Prometheus and Grafana

· Perform exploratory data analysis and visualization to support model development

· Collaborate with cross functional teams supporting computer vision, natural language processing, and generative AI initiatives Qualifications:

· Proficiency in Python with experience using NumPy and scikit learn

· Strong understanding of machine learning algorithms including supervised and unsupervised learning

· Experience with deep learning frameworks such as TensorFlow, PyTorch, or Keras

· Hands on experience as an HPC engineer supporting GPU accelerated environments

· Experience deploying machine learning models into production environments

· Knowledge of neural networks, ensemble methods, gradient boosting, and transformer based models

· Experience with hyperparameter tuning, transfer learning, and generative AI techniques

· Experience with Linux system administration using RHEL or CentOS

· Strong understanding of API development and security best practices

· Experience collecting and analyzing metrics to identify performance issues and implement fixes Tools and Technologies:

· Docker, Kubernetes, Jupyter, MLFlow, GitHub, Terraform, Jenkins, Hugging Face

· Triton Inference Server and TRT LLM

· Prometheus and Grafana

· SLURM workload manager

· Enroot, Pyxis, and Podman container runtimes

· Plotly, Seaborn, and matplotlib

· Databases including Oracle, MS SQL, MongoDB, Redis, and MySQL Desired Qualifications:

· Experience with data cleaning, feature scaling, and normalization

· Experience creating vector embeddings

· Experience with AWS services including SageMaker, Lambda, and EC2

· Programming experience creating UI and UX using Angular, HTML, CSS, and JavaScript

· SQL and PL SQL scripting experience