About the job
Join our dynamic team at gsstech-group as a Senior Technology Engineer, where you will leverage your expertise in AI/ML platforms, MLOps, and scalable inference systems. In this pivotal role, you will be responsible for the design, deployment, and optimization of cutting-edge AI-driven solutions in both on-premises and cloud environments, with a particular emphasis on Generative AI and Large Language Model (LLM)-based applications.
Key Responsibilities:
- Architect, develop, and sustain containerized applications utilizing OpenShift, OpenShift AI, Kubernetes, and Helm Charts.
- Integrate and fine-tune AI inference engines like Triton Inference Server and vLLM for optimal model serving performance.
- Oversee the complete model lifecycle management from deployment to monitoring, scaling, and maintenance in production settings.
- Implement comprehensive monitoring and alerting frameworks with tools such as Prometheus and Grafana.
- Collaborate on groundbreaking Generative AI and LLM initiatives, including Agentic AI systems.
- Establish and manage CI/CD pipelines using Jenkins, Ansible, Groovy, and Terraform.
- Create automation tools and scripts with Python to enhance system efficiency and reliability.
- Design and administer AI/ML solutions on AWS Cloud, utilizing services like Amazon SageMaker and AWS Bedrock (preferred).
- Enhance AI platforms across hybrid environments (on-premise and cloud).
- Ensure systems are scalable, resilient, and high-performing.
- Contribute to architectural design decisions and shape the future roadmap of AI platform capabilities.

