AI Optimization Engineer

Job Summary

We are seeking an AI Optimization Engineer to support enterprise AI/ML initiatives with a focus on performance optimization, scalable infrastructure, and production deployment. The ideal candidate will have hands-on experience with large language models (LLMs), GPU-accelerated environments, and high-performance computing (HPC) platforms.

Key Responsibilities

• Design, optimize, and deploy machine learning and deep learning models into production
• Build and manage scalable infrastructure for AI/ML workloads, including LLMs
• Configure and maintain GPU-accelerated clusters for large-scale processing
• Implement model optimization techniques (pruning, quantization, distillation)
• Deploy models using containerized and microservices-based architectures
• Develop secure REST APIs using Flask for inference and orchestration
• Configure and optimize Triton Inference Server for model serving
• Manage job scheduling and automation using SLURM
• Monitor system and model performance using Prometheus and Grafana
• Perform exploratory data analysis (EDA) and visualization
• Collaborate with cross-functional AI teams (NLP, Computer Vision, GenAI)

Required Skills & Qualifications

• Strong Python programming (NumPy, scikit-learn)
• Experience with ML/DL frameworks: TensorFlow, PyTorch, or Keras
• Hands-on experience with HPC and GPU environments
• Strong knowledge of ML algorithms (supervised & unsupervised learning)
• Experience deploying ML models into production
• Understanding of neural networks, transformers, and ensemble methods
• Experience with hyperparameter tuning and transfer learning
• Linux administration (RHEL/CentOS)
• API development experience (Flask, REST)
• Strong troubleshooting and performance optimization skills

Tools & Technologies

• Containers & Orchestration: Docker, Kubernetes, Podman, Enroot, Pyxis
• ML & AI Tools: MLflow, Jupyter, Hugging Face
• Inference & Optimization: Triton Inference Server, TRT-LLM
• Monitoring: Prometheus, Grafana
• CI/CD & Infra: GitHub, Jenkins, Terraform
• Databases: Oracle, MS SQL, MySQL, MongoDB, Redis
• Visualization: Matplotlib, Seaborn, Plotly
• Scheduling: SLURM

Preferred Qualifications

• Experience with AWS (SageMaker, EC2, Lambda)
• Knowledge of vector embeddings and generative AI
• Experience with data preprocessing (cleaning, scaling, normalization)
• Frontend exposure (Angular, HTML, CSS, JavaScript)
• SQL / PL-SQL scripting

JOBID: 12335