Senior Staff Engineer Software - AI/Agentic AI [T500-30276]

About Albertsons:

As a leading food and drug retailer in the United States, Albertsons Companies, Inc. (ACI) operates over 2,200 stores across 34 states and the District of Columbia. Our well-known global banners, including Albertsons, Safeway, Vons, Jewel-Osco and others. Our success is built upon a united team approach, driven by the desire to understand and enhance the customer experience. This customer-centric focus not only inspires innovation but has also led to remarkable achievements across our digital platforms and omnichannel strategies. By constantly pushing the boundaries of retail, we have transformed shopping into an experience that is not just easy and efficient, but also fun and engaging. Over the past year, we have taken bold, strategic steps to migrate and modernize our enterprise data hub on Google Cloud, revolutionizing our data capabilities, thus becoming the first fully cloud-based grocery tech company.

About Tech Hub in India:

Albertsons Companies India (ACI India) is part of Albertsons Companies Inc. global workforce. As Albertsons’ first significant strategic investment in India, it serves as a collaborative hub, supporting Albertsons in driving innovation and efficiency across Technology, Digital, and other key business functions. The employees at the India GCC will play a pivotal role in enhancing the company’s digital transformation, customer engagement, and operational excellence.

We are excited to announce an opening for Senior Staff Software Engineer, AI Engineering (AIDLC) at ACI. Please find below the details of the role and its responsibilities.

Roles & responsibilities:

• Set agent architecture patterns for the AIDLC (AI-driven development lifecycle) pod: orchestration, tool and function calling, MCP, memory and state management, context engineering and RAG.
• Design and build multi-agent systems across the software development lifecycle: requirements and design, code review before merge, security-finding remediation, test generation, release and path to production, and SRE and incident support.
• Build and maintain MCP servers, including code knowledge graphs exposed over MCP, so agents can query large Java/Spring and React/Angular codebases.
• Own eval standards for the pod. Define golden datasets, LLM-as-judge scoring with human calibration and regression suites, and make passing evals a release gate for every agent change.
• Own observability standards: tracing, logging and cost reporting for agents in production, so any agent action can be reconstructed.
• Design guardrails for agents that act on source control, CI/CD and cloud: least-privilege tool access, prompt-injection defence, human-in-the-loop approval points, and trust and delegation rules between agents.
• Review agent designs and agent pull requests from other engineers, and raise the quality bar through reviews and written patterns.
• Mentor Staff, mid-level and junior engineers on agent design, evals and debugging agent failures.
• Write production code every week. Use agentic coding tools daily (e.g. Claude Code, GitHub Copilot, Cursor) and show the pod how to use them well.
• Measure agent impact against the pre-agent baseline: delivery speed and cost, defects, security findings, cycle time and change failure rate. Own the technical side of those numbers.
• Track model and token cost and design for it through model routing, caching and context management.
• Evaluate frameworks, models and vendor tools for the pod and recommend build or buy to the Sr. Manager.
• Partner with Security, Cloud, Data, Product and Enterprise Architecture teams so agents meet security, risk and compliance standards.

Experience Required:

• AI experience is a MUST. You have built and deployed LLM agents or agentic workflows in production, used by real users, including at least one multi-agent system, with evals and tracing in place. Describe it in your application or link a repo or demo.
• 12+ years of software engineering experience, including hands-on delivery of distributed systems.
• Hands-on programming in Python, Java or TypeScript, used to build agents and the services around them. The agents work on Java/Spring and React/Angular codebases.
• Multi-agent orchestration is required: task decomposition, delegation, handoffs, shared state and failure handling. Frameworks are examples only (e.g. LangGraph, LangChain/LangSmith, Claude Agent SDK, OpenAI Agents SDK, Google ADK).
• Depth in tool/function calling, M…