Generative AI Engineer
Persistent
Persistent
Persistent is seeking a skilled Generative AI Engineer to develop advanced AI solutions. This role focuses on leveraging Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Agentic AI frameworks to build enterprise-grade applications. You will have the opportunity to work with cutting-edge AI technologies and drive innovation within a dynamic environment.
The position offers a chance to contribute to groundbreaking projects, integrating AI seamlessly with existing enterprise systems and creating intelligent assistants and automation solutions. Join a team that values talent development and offers growth opportunities.
Design, develop, and maintain Generative AI applications utilizing LLMs and frameworks like LangChain or Semantic Kernel.
Build RAG solutions and integrate them with enterprise knowledge bases and vector databases.
Optimize prompts for enhanced response quality, accuracy, performance, and cost efficiency.
Develop scalable backend services and orchestration workflows for AI-driven applications.
Implement Agentic AI solutions for autonomous reasoning and task execution.
Conduct testing, validation, and benchmarking of AI models and applications, ensuring responsible AI practices and compliance.
A minimum of 5-8 years in software engineering, AI engineering, or application development is required.
Demonstrated experience building enterprise-grade Generative AI applications is essential.
Strong proficiency in Python and backend development, coupled with a solid understanding of LLMs and enterprise AI use cases.
Experience with AI platforms such as Azure OpenAI or Google Gemini, and AI orchestration frameworks like LangChain or CrewAI is crucial.
Familiarity with vector databases, semantic search, prompt engineering, and integrating AI solutions with cloud platforms (Azure, AWS, GCP) is expected.
Persistent Systems
Information Technology & Services