•You will be responsible for prompting and building use case Pipelines

•Perform the Evaluation of all the Gen-AI features and Usecase pipeline

•Strong proficiency with Python, DJANGO framework and REGEX

•Good understanding of Machine learning framework Pytorch and Tensorflow

•Knowledge of Generative AI and RAG Pipeline

•Good in microservice design pattern and developing scalable application.

•Ability to build and consume REST API

•Fine tune and perform code optimization for better performance.

•Strong understanding on OOP and design thinking

•Understanding the nature of asynchronous programming and its quirks and workarounds

•Good understanding of server-side templating languages

•Understanding accessibility and security compliance, user authentication and authorization between multiple systems, servers, and environments

•Integration of APIs, multiple data sources and databases into one system

•Good knowledge in API Gateways and proxies, such as WSO2, KONG, nginx, Apache HTTP Server.

•Understanding fundamental design principles behind a scalable and distributed application

•Creating and managing database schemas that represent and support business processes, Hands-on experience in any SQL queries and Database server wrt managing deployment.

•Implementing automated testing platforms, unit tests, and CICD Pipeline

•Proficient understanding of code versioning tools, such as GitHub, Bitbucket, ADO

•Understanding of container platform, such as Docker

•Good working knowledge on Microservices architecture, behaviour, dependencies, scalability etc.

•Experience in deploying on Cloud platform like Azure or AWS

•Familiar and working experience with DevOps tools like Azure DEVOPS, Ansible, Jenkins, Terraform

•Take care of entire prompt life cycle like prompt design, prompt template creation, prompt tuning/optimization for various Gen-AI base models

•Design and develop prompts suiting project needs

•Lead and manage team of prompt engineers

•Stakeholder management across business and domains as required for the projects

• Evaluating base models and benchmarking performance

• Implement prompt gaurdrails to prevent attacks like prompt injection, jail braking and prompt leaking

• Develop, deploy and maintain auto prompt solutions

• Design and implement minimum design standards for every use case involving prompt engineering"

AWS MLOPS