AI/ML Engineer

Summary:

• Location: Mason, OH
• Work Mode: Onsite

Responsibilities:

• Architect and deliver end-to-end LLM-powered applications and agentic workflows using Python.
• Design and implement RAG (Retrieval-Augmented Generation) pipelines over enterprise data using embeddings and vector databases.
• Build multi-step, tool-using agents with planning, execution, and memory capabilities using frameworks such as LangChain.
• Integrate AI systems with APIs, backend services, and cloud platforms.
• Establish evaluation, reliability, and performance strategies, including accuracy, latency, and cost optimization.

Requirements:

• 10 years of experience in designing and building production-grade LLM-powered applications and agentic systems.
• 6 years of experience in end-to-end development of intelligent solutions from architecture to deployment leveraging Python, modern LLM frameworks, and scalable system design.
• 6 years of experience with architecting and delivering end-to-end LLM-powered applications and agentic workflows using Python.
• 6 years of experience in designing and implementing RAG pipelines over enterprise data using embeddings.
• 6 years of experience with vector databases.
• Experience in building multi-step, tool-using agents (planning, execution, memory) using frameworks such as LangChain.
• Experience in integrating AI systems with APIs, backend services, and enterprise applications.
• Experience with cloud platforms.
• Ability to establish evaluation, reliability, and performance strategies focused on accuracy, latency, scalability, and cost optimization.