LLM Integration & CI/CD Engineer PWC

We are seeking a highly skilled LLM Integration & CI/CD Engineer to bridge the gap between advanced AI research and scalable production infrastructure. In this role, you will lead the deployment, orchestration, and lifecycle management of large language models, ensuring seamless integration into our core technology stack. You will be instrumental in building robust pipelines that enable rapid iteration and reliable delivery of AI-driven solutions. Key Deliverables Architect and maintain automated CI/CD pipelines specifically tailored for high-performance LLM deployment and model versioning. Design and implement scalable cloud infrastructure on AWS and Azure to support intensive AI workloads and model inference. Collaborate with data science and engineering teams to optimize model serving latency, throughput, and resource utilization. Establish comprehensive monitoring, logging, and observability frameworks to track model performance and infrastructure health in real-time. Automate the provisioning and configuration of GPU-accelerated environments to ensure consistent development and production parity. Implement security best practices for model deployment, data handling, and API access management within cloud environments. Essential Requirements Minimum of 4-7 years of professional experience in DevOps, Cloud Engineering, or MLOps roles. Proven expertise in managing cloud infrastructure on AWS and Azure, including container orchestration and serverless architectures. Strong proficiency in building and maintaining CI/CD pipelines for complex software and AI-driven applications. Deep understanding of LLM deployment patterns, including model quantization, fine-tuning workflows, and inference optimization. Demonstrated ability to manage infrastructure as code (IaC) and automate cloud resource provisioning. Preferred Qualifications Experience with MLOps platforms and tools such as MLflow, Kubeflow, or similar model lifecycle management systems. Familiarity with vector databases and retrieval-augmented generation (RAG) architecture. Background in optimizing high-concurrency distributed systems. Relevant certifications in AWS or Azure cloud architecture. What We Offer Opportunity to work at the forefront of generative AI integration within a large-scale enterprise environment. Access to complex, high-impact projects that challenge technical boundaries and foster professional growth. A collaborative, cross-functional team environment that values technical excellence and innovative problem-solving. Exposure to cutting-edge cloud technologies and industry-leading AI development practices. Success in This Role Success is defined by your ability to reduce deployment friction and ensure the stability of our AI services as we scale. You will be measured by the reliability of your CI/CD pipelines, the efficiency of our model serving infrastructure, and your proactive approach to solving complex integration challenges. Additional Information This position is strictly an onsite role based in Bengaluru, requiring daily presence at our office. Expect to work in a fast-paced environment with frequent collaboration across global engineering and data science teams. .