Rhapsody
AI Engineer
Rhapsody is building a platform-wide AI foundation to power intelligent assistants, agentic automation systems, and embedded machine learning features across our product ecosystem. We're looking for an AI Engineer to join our growing AI team and lead the development of LLM-based workflows, retrieval-augmented generation (RAG) systems, and agentic AI behavior. As an AI Engineer, you will focus on designing the intelligence layerprompt strategies, embedding pipelines, retrieval logic, and multi-step reasoningbehind AI systems that serve both internal and external users. You'll work at the frontier of applied AI, experimenting with the latest models and techniques, and building smart, composable workflows that power end-user features. While you'll collaborate closely with platform engineers to deploy stable systems, your focus will be on exploring new capabilities, designing intelligent behavior, and validating AI performance. We're looking for someone who is not only technically strong, but deeply curious and open-mindedsomeone who stays current with the latest models, tools, and research, and thrives in an experimental environment where rapid iteration, learning, and exploration lead to high-impact breakthroughs. Key Responsibilities: Architect and implement LLM-powered systems, including RAG pipelines and agentic workflows Prototype, test, and refine multi-step reasoning and tool-use behavior (agentic AI) Design prompt strategies, chunking logic, context management, and fallback flows Evaluate emerging LLM models, tools, and architecturesand identify how they can improve existing systems or unlock new capabilities Collaborate with AI Platform Engineers to deploy LLM systems into production environments Partner with platform engineers to ensure AI systems are observable, debuggable, and performant in production Contribute to shared tools and frameworks for prompt versioning, cost control, and observability Collaborate on data sciencedriven features such as forecasting, prediction, and evaluation pipelines when needed Work with product teams to align assistant behaviors with real user needs and domain-specific logic Qualifications: Required: 5+ years of experience in software engineering or applied AI/ML roles, with strong proficiency in Python and a track record of building intelligent systems or AI-powered features Hands-on experience building and deploying LLM-based systems (e.g., OpenAI, Claude, Mistral, or open-source models) Understanding of prompt engineering, tokenization, context windows, and LLM evaluation Familiarity with RAG systems, vector databases (e.g., FAISS, Pinecone, Weaviate), and embedding generation Experience designing end-to-end AI pipelines or systems that incorporate retrieval, prompting, or agent logic Ability to build well-structured, maintainable code that enables experimentation and handoff to production teams Comfort working in iterative, fast-paced environments Preferred: Experience with LangChain, LlamaIndex, or custom agentic frameworks Exposure to observability, metrics, and cost-performance tuning for LLM-based systems Familiarity with data science techniques or workflows (e.g., feature engineering, model evaluation, experimentation) is a plus Prior work in AI for healthcare or other complex domains is a plus Education: Bachelor's or Master's degree in Computer Science, Engineering, AI/ML, or a related technical field (or equivalent experience)
Rhapsody is building a platform-wide AI foundation to power intelligent assistants, agentic automation systems, and embedded machine learning features across our product ecosystem. We're looking for an AI Engineer to join our growing AI team and lead the development of LLM-based workflows, retrieval-augmented generation (RAG) systems, and agentic AI behavior. As an AI Engineer, you will focus on designing the intelligence layerprompt strategies, embedding pipelines, retrieval logic, and multi-step reasoningbehind AI systems that serve both internal and external users. You'll work at the frontier of applied AI, experimenting with the latest models and techniques, and building smart, composable workflows that power end-user features. While you'll collaborate closely with platform engineers to deploy stable systems, your focus will be on exploring new capabilities, designing intelligent behavior, and validating AI performance. We're looking for someone who is not only technically strong, but deeply curious and open-mindedsomeone who stays current with the latest models, tools, and research, and thrives in an experimental environment where rapid iteration, learning, and exploration lead to high-impact breakthroughs. Key Responsibilities: Architect and implement LLM-powered systems, including RAG pipelines and agentic workflows Prototype, test, and refine multi-step reasoning and tool-use behavior (agentic AI) Design prompt strategies, chunking logic, context management, and fallback flows Evaluate emerging LLM models, tools, and architecturesand identify how they can improve existing systems or unlock new capabilities Collaborate with AI Platform Engineers to deploy LLM systems into production environments Partner with platform engineers to ensure AI systems are observable, debuggable, and performant in production Contribute to shared tools and frameworks for prompt versioning, cost control, and observability Collaborate on data sciencedriven features such as forecasting, prediction, and evaluation pipelines when needed Work with product teams to align assistant behaviors with real user needs and domain-specific logic Qualifications: Required: 5+ years of experience in software engineering or applied AI/ML roles, with strong proficiency in Python and a track record of building intelligent systems or AI-powered features Hands-on experience building and deploying LLM-based systems (e.g., OpenAI, Claude, Mistral, or open-source models) Understanding of prompt engineering, tokenization, context windows, and LLM evaluation Familiarity with RAG systems, vector databases (e.g., FAISS, Pinecone, Weaviate), and embedding generation Experience designing end-to-end AI pipelines or systems that incorporate retrieval, prompting, or agent logic Ability to build well-structured, maintainable code that enables experimentation and handoff to production teams Comfort working in iterative, fast-paced environments Preferred: Experience with LangChain, LlamaIndex, or custom agentic frameworks Exposure to observability, metrics, and cost-performance tuning for LLM-based systems Familiarity with data science techniques or workflows (e.g., feature engineering, model evaluation, experimentation) is a plus Prior work in AI for healthcare or other complex domains is a plus Education: Bachelor's or Master's degree in Computer Science, Engineering, AI/ML, or a related technical field (or equivalent experience)