Principal Engineer, Artificial Intelligence

at  Carmax

8116 - Midtown Office - 2220 W. Broad Street, Richmond, Virginia, 23220
CarMax, the way your career should be!

MINIMUM QUALIFICATIONS:

• Bachelor’s Degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience
• Optional for sponsorship needs: Master’s Degree in Computer Science, Computer Engineering, or relevant technical field
• In depth experience using large language models (LLMs) with semantic search frameworks for chatbot implementations
• 7+ years of experience in one or more of the following areas: machine learning/artificial intelligence, cloud computing, systems engineering
• In depth knowledge developing and debugging in Python, and experience with scripting languages such as shell scripts
• Experience communicating and working across functions to drive organization-wide solutions
• Ability to positively influence team norms, culture, and technical vision

PREFERRED QUALIFICATIONS:

• Previous experience deploying large-scale applications on Azure
• Experience developing, evaluating, and integrating continuous integration and deployment (CI/CD) of prompt engineering with feedback loops for Generative AI applications

SOFTWARE ENGINEERING SPECIFIC QUALIFICATIONS AND REQUIREMENTS:

• Experience developing generative AI applications using Azure OpenAI Service
• Experience with information retrieval services such as Azure AI search
• Leveraging development tools to design prototyping, prompt engineering, testing, and evaluation of LLM-based applications (PromptFlow)
• Experience in DevOps practices, testing frameworks, and CI/CD
• Experience developing AI orchestration layers (Semantic Kernel)
• Managing the security, versioning, and observability across APIs
• In depth knowledge developing and debugging in Python
• Experience with scripting languages such as shell scripts

Work Location and Arrangement: This role will be based out of one of the following locations and have a Hybrid work arrangement:

• Richmond, VA Technology Innovation Center
• Dallas, TX Technology Hub

Work Authorization: Applicants must be currently authorized to work in the United States on a full-time basis. Sponsorship will be considered for this specific role.

ESSENTIAL RESPONSIBILITIES:

• Suggest, collect, and translate requirements into an effective feature roadmap for organization platform capabilities
• Evaluate and recommend tradeoffs of features to the platform that allow use case owners to refine output generation and new technology offerings in the space
• Be a key partner in driving direction and goals for the team, both in terms of individual project impacts but also overall standards for Generative AI utilization in the organization
• Lead process and technology teams in developing integration, end-to-end, and UAT test strategy as well as testing activities
• Lead escalation of production performance and evaluation issues that require in-depth knowledge of techniques such as prompt engineering, fine-tuning, and document embedding and retrieval
• Help drive the broader understanding of the use of Generative AI by interfacing with key roles in Operations, Legal, Security, and Technology
• Stay on top of industry trends and best practices to continuously improve what we do and ensure our customer experience is the best it can be
• Lead, mentor, and develop other engineers using technical expertise, best practices and industry standards for Generative AI systems

Work Location and Arrangement: This role will be based out of one of the following locations and have a Hybrid work arrangement:

• Richmond, VA Technology Innovation Center
• Dallas, TX Technology Hu