Senior Python AI Engineer
Persistent
Persistent
Join a leading digital engineering partner leveraging AI and platform-driven solutions to help clients anticipate the future and gain a competitive edge. We empower organizations globally, including top Fortune 50 companies and major banks, with innovative approaches. Our commitment to client success and agility fuels our sustained growth. We are recognized for innovation, leadership, and inclusion, with strong revenue performance and a global team of over 27,500 professionals.
This role focuses on designing, developing, and deploying enterprise-grade AI solutions, intelligent agents, and scalable Generative AI applications. You will be instrumental in building next-generation AI-powered systems.
Architect and implement AI-powered applications using Python and advanced Generative AI frameworks. Develop and deploy Retrieval-Augmented Generation (RAG) solutions, integrating enterprise knowledge bases and vector databases. Build sophisticated Agentic AI workflows and multi-agent systems leveraging LangChain and LangGraph. Design, refine, and evaluate prompts for Large Language Model applications. Seamlessly integrate enterprise systems with leading LLM providers like OpenAI, Azure OpenAI, Claude, and Gemini. Develop scalable APIs and microservices using FastAPI for robust backend solutions. Create intelligent automation solutions, including conversational AI assistants, copilots, and chatbots.
Utilize embedding models, vector stores, semantic search, and retrieval pipelines for advanced AI capabilities. Implement robust AI governance, security, and responsible AI best practices. Optimize model performance, latency, cost, and response quality for production readiness. Collaborate closely with product owners, architects, data scientists, and engineering teams to deliver impactful AI-driven solutions. Conduct comprehensive testing, debugging, monitoring, and troubleshooting of AI applications.
A minimum of 6 to 8 years of comprehensive software development experience, with exceptional proficiency in Python. Proven hands-on expertise in developing Generative AI applications. Deep understanding and practical application of Prompt Engineering techniques and prompt optimization. Strong development experience with LangChain and LangGraph frameworks. Demonstrated experience in building enterprise-grade Retrieval-Augmented Generation (RAG) solutions. Practical experience with Large Language Models (LLMs) and AI Agent architectures. Experience integrating with major LLM providers such as OpenAI, Azure OpenAI, Claude, and Gemini. Solid knowledge of vector databases, embeddings, semantic search, and retrieval systems. Experience designing and developing REST APIs using FastAPI. Understanding of microservices architecture and scalable backend development principles.
Experience working with both structured and unstructured data sources for AI applications. Familiarity with model evaluation, prompt testing, and AI performance optimization techniques. Exposure to cloud environments like Azure, AWS, or Google Cloud Platform. Strong analytical, problem-solving, and debugging capabilities. Experience working within Agile/Scrum methodologies. Excellent communication and collaboration skills are essential.
Persistent Systems
IT Services and Consulting