Generative AI Engineer – Python, LLM, Agentic Workflows

Role Overview:

• Contribute to the development and enhancement of Generative AI capabilities within enterprise applications.

• Work alongside senior engineers to implement agentic workflows, build backend services, integrate LLM-based features, and support Retrieval Augmented Generation (RAG) systems.

• Requires strong programming foundations, hands-on experience with Python, and growing expertise in modern GenAI frameworks.

Role

Description:

Generative AI Feature Development:

• Develop and enhance Generative AI features within enterprise-grade applications under the guidance of senior engineers.

• Implement agentic workflows, prompt-based solutions, and LLM integrations using established frameworks and cloud-based AI services.

Backend & API Engineering:

• Build and integrate backend services and REST APIs to support GenAI features across platforms.

RAG (Retrieval-Augmented Generation) Support:

• Support RAG implementations, including embedding generation, vector database integration, and contextual data retrieval.

• Assist in model inference, evaluation, and continuous improvement of AI outputs.

Full-Stack GenAI Contribution:

• Contribute to full-stack GenAI applications, including backend logic and basic frontend integration.

Engineering Best Practices:

• Follow modern engineering best practices: code reviews, test-driven development (TDD), CI/CD pipelines, and secure coding standards.

Collaboration & Agile Delivery:

• Collaborate within Agile teams, participate in sprint ceremonies, and continuously develop expertise in emerging GenAI technologies.