Apr 2023 – Present · 2 yrs 11 mos · Delhi, India

• As an LLMOps Engineer, I specialize in deploying, managing, and optimizing large language models (LLMs) in production environments. My work involves developing Python code, architecting scalable systems, and automating CI/CD pipelines to streamline model deployment and operations. Key contributions include:
• Python Development: Created and optimized Python scripts for training, fine-tuning, and deploying custom LLMs, enhancing their performance and applicability.
• Pipeline Automation: Developed multi-branch CI/CD pipelines using Jenkins and Ansible, reducing deployment time by 30% and ensuring seamless model integration.
• Model Optimization: Led initiatives to improve LLM accuracy and efficiency, managing the conversion and retrieval of large-scale document datasets.
• Infrastructure Scaling: Implemented cloud-based scaling solutions and managed GPU clusters, ensuring high availability and optimal model performance.
• Collaboration: Promoted best practices in version control and code reviews, contributing to multiple GitHub repositories for robust and maintainable codebases.
• Real-time Data Integration: Integrated LLMs with MongoDB for real-time data processing, developing chatbot interfaces and APIs for enhanced user interaction.

Oct 2021 – Apr 2023 · 1 yr 6 mos · Delhi, India

• Work involves:
• Provisioning automated CI, CD pipelines and creating highly reliable, secure & scalable infrastructure.
• Creating a custom toolkit to support the engineering team.Work involves:
• Creating a custom toolkit to support the engineering team.