FullStack GEN AI Engineer

The ideal candidate will have a proven track record of working across the tech stack, from backend systems and APIs to frontend user interfaces, ensuring a seamless integration of AI models into production ready systems. The candidate will need to demonstrate he or she has a strong technical background, is curious, and has exceptional communication and problem-solving skills.

Key responsibilities include:

• Build scalable web and cloud-based applications integrating generative AI models.

• Build and maintain a robust agentic architecture, APIs, and microservices using technologies such as Python.

• Develop user friendly, responsive user interfaces using technologies such React.

• Design and maintain Azure based infrastructure for hosting and scaling AI solutions.

• Monitor and improve system performance.

• Implement best practices for secure and scalable application design, data storage, and API handling.

• Work closely with cross-functional team members, including Product Owners, Scrum Master, Lead Data Architect, UI/UX, and Application Owners to ensure the end-to-end delivery of user stories.

• Participate in Scrum ceremonies and actively maintain your cards on the scrum board.

• Maintain comprehensive technical documentation for all systems and processes.

Skills and Abilities:

• Proficient in backend development using Python.

• Strong experience with frontend frameworks using React.

• Hands-on knowledge and experience with Microsoft Azure cloud services, including Azure Foundry, Functions, Blob, and container tools such as Azure Kubernetes.

• Build and manage data pipelines ensuring high-quality data is available for AI model training and deployment.

• Experience working with structured and unstructured data that span across SQL databases and NoSQL databases such as CosmosDB.

• Proficient with API development and management.

• Experience building and working with CI/CD pipelines and version control tools like GIT.

• Experience developing and delivering event driven architectures.

• Experience in using and implementing open-source large language models such as Llama, Mistral, GPT, and assorted embedding models • Experience doing prompt engineering.

• Experience working with agile delivery methodologies and working in an agile delivery team.

• Curious. Stays abreast of current and upcoming technologies and tools.