Generative AI Engineer
Persistent
Persistent
Join Persistent as a Generative AI Engineer and shape the future of enterprise solutions. You will be instrumental in designing, developing, and deploying advanced AI applications leveraging LLMs, RAG, and Agentic AI frameworks. This role is perfect for innovators passionate about building intelligent assistants and automation that integrate seamlessly with enterprise systems, driving significant business impact.
We are an AI-led, platform-driven Digital Engineering and Enterprise Modernization partner, working with industry leaders across diverse sectors. Our culture thrives on a disruptor's mindset, client success, and agility. Be part of a recognized organization committed to innovation, leadership, and inclusion, with a strong track record of growth and global reach.
Design, develop, and maintain cutting-edge Generative AI applications powered by Large Language Models (LLMs). Build intelligent assistants and AI-powered business applications using frameworks like LangChain, Semantic Kernel, or CrewAI. Develop robust Retrieval-Augmented Generation (RAG) solutions for efficient enterprise knowledge retrieval. Optimize prompts to enhance response quality, accuracy, performance, and cost-effectiveness. Integrate AI services with enterprise applications, APIs, databases, and cloud platforms. Create scalable backend services and orchestration workflows for AI-driven applications. Implement Agentic AI solutions for autonomous reasoning, planning, and task execution. Manage and build vector search solutions using embeddings and semantic retrieval techniques. Conduct thorough testing, validation, and benchmarking of AI models and applications. Evaluate AI solution effectiveness based on quality, reliability, and business impact. Uphold responsible AI practices, governance, and compliance standards. Collaborate with cross-functional teams including architects, data engineers, and application developers. Develop proof-of-concepts and pilot solutions for emerging AI use cases. Produce comprehensive technical documentation, architecture diagrams, and implementation guides. Participate actively in code reviews, architecture reviews, testing, deployment, and production support. Implement robust monitoring, logging, observability, and performance tracking for AI systems. Continuously explore and evaluate new Generative AI, Agentic AI, and LLM technologies.
Possess 6-10 years of experience in software engineering, AI engineering, machine learning, or application development. Demonstrate hands-on experience building enterprise-grade Generative AI applications. Exhibit a strong understanding of Large Language Models (LLMs) and their enterprise applications. Have experience with AI platforms such as Azure OpenAI, OpenAI, Anthropic Claude, or Google Gemini. Showcase strong expertise in Python programming and backend development. Proficiently implement Retrieval-Augmented Generation (RAG) architectures and enterprise knowledge retrieval solutions. Demonstrate hands-on experience with vector databases, semantic search, embeddings, and retrieval systems. Experience building Agentic AI applications and intelligent workflow automation solutions is essential. Possess knowledge of prompt engineering and LLM optimization techniques. Familiarity with AI orchestration frameworks like LangChain, LangGraph, Semantic Kernel, CrewAI, or AutoGen is highly valued. Understand Natural Language Processing (NLP) and Machine Learning concepts. Experience integrating AI solutions with APIs, databases, enterprise applications, and cloud services. Strong understanding of software design, development, testing, deployment, and maintenance practices. Familiarity with cloud platforms such as Azure, AWS, or Google Cloud Platform. Experience with Git, CI/CD pipelines, testing frameworks, and DevOps practices. Exhibit strong analytical, troubleshooting, and problem-solving capabilities. Possess excellent communication and stakeholder management skills.
Persistent Systems
Information Technology & Services