Senior AI Engineer - Agentic Systems and LLM

This position is listed on behalf of a partner company, which manages all applications and next steps. Our partner is looking for a Senior AI Engineer – Agentic Systems and LLM based in the United States. We are looking for an experienced Senior AI Engineer to design, develop, and deploy production-ready AI applications powered by Large Language Models (LLMs) and agentic systems. In this fully remote role, you will take ownership of the entire development lifecycle, from solution architecture and implementation to deployment and optimization. You will build intelligent, scalable applications using Python, modern LLM frameworks, and advanced AI technologies. Your work will include developing Retrieval-Augmented Generation (RAG) pipelines, multi-step autonomous agents, and integrations with enterprise systems. You will also contribute to improving AI performance, reliability, accuracy, and cost efficiency. This is an exciting opportunity to shape practical AI solutions and drive innovation in a collaborative, technology-focused environment. Accountabilities Design, architect, and deliver end-to-end LLM-powered applications and agentic workflows using Python. Develop and implement Retrieval-Augmented Generation (RAG) pipelines using enterprise data, embeddings, and vector databases. Build sophisticated, multi-step AI agents capable of planning, executing tasks, using external tools, and maintaining contextual memory. Leverage modern AI development frameworks, including LangChain, LangGraph, and AutoGen, to orchestrate intelligent workflows. Integrate AI-powered applications with APIs, backend services, and cloud-based platforms. Establish and implement strategies for evaluating AI systems, ensuring accuracy, reliability, scalability, and performance. Monitor and optimize application performance, focusing on latency, operational costs, and overall solution efficiency. Take ownership of the complete development lifecycle, from technical architecture and development through deployment and continuous improvement. Requirements 2–3 years of hands-on experience developing and implementing agentic AI workflows. Strong proficiency in Python, with demonstrated experience building and deploying production-grade backend applications. Practical experience developing LLM-powered applications, including prompt engineering, LLM orchestration, and integration. Proven expertise in RAG architectures, embeddings, semantic search, and vector database technologies. Hands‑on experience with agentic AI frameworks such as LangChain, LangGraph, or AutoGen. Strong system design and software architecture skills, with experience developing and scaling cloud-based applications. Ability to integrate AI solutions with APIs, enterprise systems, and backend infrastructure. Understanding of AI evaluation methodologies and performance optimization, including accuracy, latency, and cost management. Strong analytical, problem-solving, and communication skills, with the ability to take ownership of complex technical projects. Experience in the healthcare insurance industry, particularly within the payer domain, is a strong advantage. Compensation $60 per hour Work arrangement 100% remote within the United States Flexibility Remote working opportunity, with flexibility for the right candidate Career development Opportunities to work with advanced AI technologies, LLM applications, and emerging agentic systems Professional growth Exposure to enterprise-scale AI projects and innovative technology solutions Additional perks Employee discounts and career flexibility and growth opportunities. #J-18808-Ljbffr