Director, Agentic Engineering (P4474)

84.51° Overview:

84.51° is a retail data science, insights and media company. We help The Kroger Co., consumer packaged goods companies, agencies, publishers and affiliates create more personalized and valuable experiences for shoppers across the path to purchase.

Powered by cutting-edge science, we utilize first-party retail data from more than 62 million U.S. households sourced through the Kroger Plus loyalty card program to fuel a more customer-centric journey using 84.51° Insights, 84.51° Loyalty Marketing and our retail media advertising solution, Kroger Precision Marketing.

84.51° follows a 5‑day in‑office work schedule to support collaboration, alignment, and team connection.

Join us at 84.51°!

__________________________________________________________

Director, Agentic Engineering

Grade G4 | Engineering | AI Enablement, 84.51° and Kroger Technology & Digital (KTD) | Reports to [Senior Director/VP, AI Enablement] | Location [Cincinnati, OH/Chicago, IL]

About 84.51 and the opportunity

84.51° is Kroger’s data science, insights and AI company. Kroger is a roughly $150B Fortune 20 retailer, and the software and AI products our teams build shape how that business serves its customers every day. This role is an enterprise-level opportunity to reinvent how software and AI products are built across 84.51°, KTD and Kroger, and to set the standard for how engineering at this scale works alongside AI agents.

The foundation is already in motion. Claude Code is generally available to technologists under an enterprise-managed configuration, GitHub Copilot and Microsoft 365 Copilot are in the hands of thousands of associates, Claude Cowork and Claude Design have waitlists of eager users, AI Hub is becoming the front door for “how to AI at Kroger”, and a managed agent platform and the first lighthouse projects are live. The next step is to turn strong tools and early wins into a measurable, repeatable, enterprise-wide way of building software.

Role Summary

The Director, Agentic engineering will move our organization from AI-assisted coding to a genuinely agentic engineering organization. You will redesign the end-to-end software development lifecycle (plan, design, build, test, deploy and operate) around AI agents, with people owning judgment at the critical gates: product intent, architecture, design and risk approval.

You will own the developer-facing AI ecosystem end to end: the AI SDLC operating model, the rollout and adoption of coding agents such as Claude Code, new autonomous agentic systems such as Devin, the AI Developer Portal that gives every builder a governed, self-service path to models, agents and tools, and the engineering experience surfaced through AI Hub. You will partner directly with the C-suite to shape the strategy and investment case and keep them informed of progress with clarity and candor. The goal is materially faster delivery, with quality, security, reliability and cost held at or better than today’s bar.

The AI Engineering Ecosystem You Will Lead

The table below summarizes the capabilities this role owns or shapes, and the mandate for each.

Capability

What it is

Your mandate

AI SDLC operating model

The agentic lifecycle from intent to production, with human gates by risk tier

Define, pilot with lighthouse teams and scale through a repeatable playbook

Claude Code

Primary enterprise coding agent, generally available under a managed configuration

Drive adoption to the default way of working; govern configuration, skills and MCP access; prove ROI

Claude Cowork, Claude Design and Microsoft 365 Copilot

Agentic tools for knowledge work, design and everyday productivity

Extend agentic workflows safely to product, design, analytics and other builders

AI Developer Portal

Self-service front door for builders: model and agent access, golden paths, templates, MCP server catalog and prompt and skill marketplace

Build and run it as a product with clear ownership, SLAs and adoption targets

AI Hub

Enterprise front door where users across 84.51°, KTD and Kroger GO learn how to use AI at Kroger

Ensure engineering journeys, approved tools and standards are surfaced and current

Integration -Managed agent platform, AI Gateway and MCP

Shared runtime, routing and tool-connectivity layer for enterprise agents

Set standards for agent harnesses, tool access, evaluation and observability

Value tracking, telemetry and FinOps

Value Tracking Dashboard, privacy-preserving usage telemetry and showback or chargeback of consumption-based AI spend

Own the unit economics and the credible story of return on AI investment

What You’ll Do

Strategy and Executive Partnership

Build the multi-year agentic engineering strategy and investment case in partnership with the C-suite, sequenced from coding agents to fully agentic delivery.

Act as the technical leader who sets priorities, removes cross-functional blockers and tracks value across 84.51°, KTD and Kroger technology teams.

Deliver regular progress narratives to the senior leadership and the Capital Committee.

Tie engineering outcomes to speed to market, released capacity and cost.

Manage strategic vendor relationships across the AI tooling stack (for example Anthropic, Microsoft and GitHub, and Google) to shape roadmaps, enterprise terms and token economics.

Serve as the internal and external voice of the transformation.

Reinvent the SDLC Operating Model

Redesign each lifecycle stage so agents handle more of the work and the hand-offs between stages are automated, from requirements and design through testing, deployment and operations.

Define how product, architecture, engineering, QA and SRE roles evolve in an agentic model, including the move from one-to-one assistance to engineers orchestrating multiple agents in parallel.

Start with lighthouse teams, prove the model with measured results, then scale it through a repeatable playbook and reusable workflow patterns.

Set the risk tiers that determine how much autonomy agents receive.

Coding Agent Rollout and Adoption

Lead the enterprise rollout of Claude Code across all technical personas, building on general availability toward deep, daily use in every delivery team.

Own the coding-agent portfolio, including GitHub Copilot, with clear guidance on when to use which tool, so that teams are not slowed by tool sprawl.

Govern the enterprise-managed configuration: approved models, permissions, MCP servers, shared skills, hooks and data-handling settings.

Embed forward deployed engineers with delivery teams to turn platform capability into real delivery outcomes and to create tight feedback loops.

Grow a practitioner community of champions, office hours, show-and-tells and internal case studies that make the new way of working visibly better.

Sequence follow-on Claude suite capabilities, such as Claude Cowork and Claude Design, without slowing core coding-agent enablement.

AI Developer Portal and Agentic Engineering Platform

Stand up the AI Developer Portal as the single self-service front door for builders: model and agent access through AI Gateway, golden-path templates, an MCP server catalog, a prompt and skill marketplace, and documentation with built-in AI assistance.

Set enterprise standards for agentic coding tools, agent harnesses and the managed agent platform.

Make institutional knowledge, engineering standards and policies machine-readable (for example as repository instructions, skills and MCP-accessible knowledge) so agents apply them consistently.

Scale CI/CD, test infrastructure and review capacity for a step-change in change volume, including deployment automation and standardized templates.

Build production feedback loops that turn incidents and regressions into fixes.

AI Hub and Enterprise Enablement

Partner with the AI Hub product team so the Hub clearly surfaces engineering journeys, approved tools, curated use cases and governance standar