GenAI & Agentic AI Engineer
Persistent
Persistent
Persistent is a digital engineering and enterprise modernization partner, powered by AI and platforms. We collaborate with leading global organizations to create a competitive advantage through advanced solutions.
This role focuses on designing, building, and deploying enterprise-grade AI solutions utilizing Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Agentic AI frameworks. You will be instrumental in developing intelligent applications and autonomous AI agents.
Lead the design and development of enterprise AI applications using LLMs and Generative AI. Build end-to-end RAG pipelines, including ingestion, embedding, indexing, and response generation. Develop and maintain connectors for enterprise applications and APIs. Implement Agentic AI workflows for planning, reasoning, and task execution. Contribute to AI orchestration frameworks, integrating RAG, workflow engines, and enterprise platforms. Develop scalable AI services and backend systems. Collaborate with stakeholders to translate business requirements into technical solutions. Drive prompt engineering, model tuning, and AI optimization. Build proofs-of-concept and reusable AI components. Ensure security, governance, and observability in AI applications. Support AI workload deployment and operations in cloud-native environments. Conduct technical reviews and establish AI engineering best practices. Mentor engineering teams and provide technical leadership. Stay updated with advancements in LLMs and Agentic AI.
5-8 years of software engineering, AI engineering, or application development experience. Minimum 2+ years of hands-on experience with Generative AI and LLM-based solutions. Strong Python programming skills and software engineering practices. Good understanding of C++ development and integrations. Experience building enterprise-scale AI applications and intelligent assistants. Strong understanding of LLMs and enterprise AI implementation patterns. Experience implementing end-to-end RAG architectures. Expertise with AI orchestration frameworks like LlamaIndex or LangChain. Strong understanding of Agentic AI workflows and multi-agent architectures. Experience with vector databases (e.g., Pinecone) and semantic search. Knowledge of embeddings, retrieval mechanisms, and reranking strategies. Experience with Model Context Protocol (MCP) integrations and AI tool-calling frameworks. Familiarity with FastMCP and modern agent orchestration approaches. Strong prompt engineering and LLM optimization skills. Experience integrating AI solutions with enterprise systems and APIs. Knowledge of software design patterns, scalability, and distributed architectures. Excellent troubleshooting, debugging, and performance optimization skills.
Persistent Systems
IT Consulting