Director, Software Engineering; P4474

Director, Software Engineering

The AI Enablement team ° is seeking a Director of Software Engineering for its Agentic Foundations team. This team is responsible for designing, developing, and maintaining the agentic backbone of the Kroger enterprise, including platforms, patterns, and tools to support the best practice development of AI agents. The Director of Engineering brings a unique mix of software engineering and AI skills to lead the technical design of platforms, patterns, and tools to support the enterprise agentic ecosystem.

The role focuses on providing technical leadership to engineering and data science development teams implementing solutions such as agent/MCP/scorer/prompt registries, agent‑related tools to aid in development and monitoring of best practice agents, and managing low‑code and no‑code agent platforms that integrate with agentic support.

• Partner with the Director of Product Management for Agentic Foundations to jointly lead the space for the Kroger enterprise.
• Lead and manage a team of engineers, guiding them in the design and development of their product/platform areas and in the management of their own reports.
• Lead and manage hiring efforts for engineers on the Agentic Foundations team, including finding interview panelists, writing interview guides and questions, and assisting with coding screening questions.
• Own and manage offshore reliability engineering teams.
• Provide in‑depth technical leadership in the scoping and implementation of enterprise‑grade solutions to support agents across the Kroger enterprise.
• Provide operational leadership across agentic platforms, ensuring enterprise‑grade reliability, observability, and incident management.
• Maintain an up‑to‑date expertise on agentic workflows, frameworks, platforms, and best practices to identify and inform new capabilities for implementation.
• Foster a collaborative and innovative team environment, encouraging professional growth and development among team members.
• Reduce the development time of the team by leveraging agentic SDLC tooling provided by the enterprise.
• Lead the abstraction of tooling and services to user‑friendly interfaces like APIs, Python packages, or UIs.
• Understand business requirements and trade‑off scale, risk, and accuracy to maximize value and translate research into consumable products or services.
• Guide the development teams to follow software development standards, including version control, documentation, testing, and support.
• Make time‑sensitive decisions and solve urgent problems without escalation.

• 7+ years professional experience with cloud‑based software architecture focused on scalability, performance, and reliability.
• 7+ years professional experience with end‑to‑end SDLC leveraging CI/CD and AIOps/MLOps, including experience with agentic SDLC tooling.
• 7+ years professional experience with large‑scale AI/ML systems, including 2+ years with GenAI and deep learning methods.
• Professional experience with production‑grade agentic systems, including concepts like design and development, evals, deployment, and monitoring.
• Professional experience with AI/ML frameworks and tooling (PyTorch, OpenAI SDK, Lang Chain, autogen).
• Professional experience with AIOps/MLOps tooling and concepts (MLflow, Model Registry, Model Monitoring).
• Professional experience with scaling and deploying AI/ML systems using tooling in Microsoft Azure and Google Cloud, including CI/CD, containerization, orchestration, and API development (in particular FastAPI).
• Professional experience with Kubernetes (AKS) and Helm.
• Professional experience with Python.
• Professional experience with infrastructure‑as‑code using Terraform.
• Professional experience leading technical teams and consulting with customers, including managing senior engineers, communicating complex technical topics, and driving outcomes in ambiguous environments.
• Skilled in partnering with product management peers to jointly define product and team direction and priorities.
• Education:
  
  Bachelor’s degree or higher in Software Engineering, Computer Science, Machine Learning, or a related field.

The…