AI/LLM Engineer

We’re building a world of health around every individual — shaping a more connected, convenient and compassionate health experience. At CVS Health®, you’ll be surrounded by passionate colleagues who care deeply, innovate with purpose, hold ourselves accountable and prioritize safety and quality in everything we do. Join us and be part of something bigger – helping to simplify health care one person, one family and one community at a time. We are seeking an experienced AI / LLM Engineer to design, develop, and operationalize advanced language model–powered applications for enterprise use cases. This role will focus on building text-based reasoning systems, Retrieval-Augmented Generation (RAG) pipelines, and scalable prompt engineering frameworks that enhance decision-making, automation, and knowledge discovery across the organization. As a key member of a cross-functional team, you will collaborate with business stakeholders to translate business requirements into reliable, explainable, and production-ready AI solutions. You will play a critical role in shaping enterprise AI capabilities by ensuring solutions are secure, responsible, and optimized for real-world performance. Design and implement LLM-powered applications that support complex, text-based reasoning and decision workflows. Develop and refine chain-of-thought-style reasoning approaches and structured prompt patterns to improve model accuracy and interpretability. Architect and build Retrieval-Augmented Generation (RAG) systems leveraging embeddings, vector search, and hybrid retrieval strategies. Create, evaluate, and optimize prompt engineering frameworks, including reusable templates, prompt libraries, and testing methodologies. Implement monitoring, logging, and feedback loops for continuous improvement of AI systems. Ensure compliance with security, governance, and Responsible AI principles. Partner with product and analytics teams to rapidly prototype and iterate AI-driven features. Tools & Technologies Programming: Python (primary), SQL LLM Platforms: OpenAI, Anthropic, Google Vertex AI Frameworks: LangChain, LlamaIndex, Semantic Kernel Vector Databases: Pinecone, Weaviate, FAISS, MongoDB Atlas Vector Search Data Processing: Spark, Pandas APIs & Services: FastAPI, Flask, REST/gRPC Cloud Platforms: AWS, Azure, Google Cloud Platform (GCP) DevOps & MLOps: Docker, Kubernetes, CI/CD tools Monitoring & Evaluation: Prompt evaluation tools, logging frameworks, observability platforms Essential Qualifications and Functions: 5+ years expereince Bachelor’s or Master’s degree in Computer Science, Engineering, Data Science, or a related field, or equivalent practical experience. Strong programming experience in Python and familiarity with software engineering best practices. Hands-on experience building production-grade AI/ML systems, not just prototypes. Experience working with Large Language Models (LLMs) and APIs. Solid understanding of: Natural Language Processing (NLP) fundamentals Machine learning concepts (training, evaluation, overfitting, bias) Practical experience with: Retrieval-Augmented Generation (RAG) systems Prompt engineering and prompt optimization Embeddings and vector search Experience designing and implementing APIs, microservices, or distributed systems. Familiarity with model evaluation techniques and performance metrics. Strong debugging and problem-solving skills in complex systems.

Experience with LLM platforms such as OpenAI, Anthropic, Google Vertex AI, or similar. Familiarity with orchestration frameworks like LangChain, LlamaIndex, Semantic Kernel, or equivalent. Experience with vector databases (e.g., Pinecone, Weaviate, FAISS, MongoDB Atlas Vector Search). Knowledge of MLOps practices, including CI/CD pipelines for AI systems. Experience deploying solutions in cloud environments (e.g., AWS, Azure, GCP). Exposure to agent-based architectures or multi-step AI workflows. Experience in financial