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 Sr. Manager, AIDLC at ACI. Please find below the details of the role and its responsibilities.

Roles & responsibilities:

- Own the AIDLC (AI-driven development lifecycle) workstream end to end: roadmap, delivery and outcomes. You report to the AI First head.
- Lead a pod of engineers who build agents 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.
- Stay hands-on for roughly a quarter of your time. Write code, build prototypes and review agent pull requests, so you judge agent designs and eval results first hand.
- Build the organization: define roles and levels, hire and onboard engineers, coach them, and set engineering standards for AI-authored and AI-assisted code.
- Set the technical direction for agent architecture: orchestration, tool and function calling, MCP servers (including code knowledge graphs exposed over MCP), memory and state management, context engineering and RAG over engineering knowledge.
- Make evals a release gate. Every agent, prompt and model change passes golden datasets, LLM-as-judge scoring calibrated against human review, and regression suites before it ships.



Require tracing and observability for agents in production.
- Define outcome metrics and measure them against the pre-agent baseline: delivery speed and cost, defects, security findings, cycle time and change failure rate. Report outcomes, not login counts or seat usage.
- Drive adoption and change management: run pilots with engineering teams, collect feedback, change how teams work, and retire agents that do not earn their place.
- Set governance and guardrails for agents that touch source control, CI/CD and cloud: least-privilege tool access, prompt-injection defence, human approval points, and an action trail that can be reviewed and reversed.
- Govern multi-agent systems: trust boundaries between agents, rules for delegation, an audit trail across agent handoffs, and the points where a human must approve.
- Govern token and compute cost: budgets, model routing, cost per successful outcome, and usage reporting to leadership.
- Run vendor and build-vs-buy evaluations for agent platforms, models and tooling, including multi-model support, with clear criteria.
- Use agentic coding tools every day (e.g. Claude Code, GitHub Copilot, Cursor) and set norms for how the pod and its partner teams use them.
- Partner with Security, Cloud, Data, Product, Enterprise Architecture and the AI governance group so agents fit existing toolchains and meet security, legal, risk and compliance standards.
- Run agents in production: reliability targets, observability, incident response and a named owner for every agent.

Experience Required:

- AI experience is a MUST. You have personally built and deployed an LLM agent or agentic workflow used by real users in the last 2 years, with evals and tracing in place. Describe it in your application or link a repo or demo.
- 12-15 years of software engineering experience, including 4+ years leading engineering teams: hiring, performance management and delivery accountability.
- 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.
- Working depth in agent orchestration, tool/function calling, MCP, memory and state management, context engineering and RAG. You can review a multi-agent design and say where it will fail. Frameworks are examples only (e.g. LangGraph, LangChain/LangSmith,



Claude Agent SDK, OpenAI Agents SDK, Google ADK).
- Experience running evals in practice: golden datasets, LLM-as-judge, regression testing, and using the results to block or approve a release.
- Experience with tracing and observability for LLM applications, and with guardrails, prompt-injection defence and human-in-the-loop design.
- Everyday use of agentic coding tools (e.g. Claude Code, GitHub Copilot, Cursor) in your own work, not only as a sponsor of them.
- Experience owning an adoption program with measured outcomes (cycle time, change failure rate, defects, cost) rather than usage counts.
- Experience managing LLM cost: token budgets, model selection and routing, and scaling agent workloads.
- Experience evaluating vendors and making build-vs-buy decisions for AI platforms.
- Cloud experience on Azure and/or Google Cloud Platform.
- Robust communication with senior leadership, engineering teams and risk partners.
- A plus: agent-to-agent (A2A) protocol, code knowledge graphs or GraphRAG, building internal developer platforms.

Competencies:

- Compassionate and kind, showing courtesy, dignity, and respect. They show sincere interest and empathy for all others.
- Foster innovation through creativity to get to a workable solution. Use analytical thinking through issues using logic and reason
- Show integrity in what is done and how it is done - without sacrificing personal/business ethics.
- Embrace an inclusion-focused mindset, seeking input from others on their work and encouraging the open expression of diverse ideas and opinions
- Team-oriented, positively contributing to team morale and willing to help.
- Learning-Focused, finding ways to improve in their field and use positive constructive feedback to grow personally and professionally
- Think strategically and proactively anticipate future problems, needs or changes in the work
- Delighting our customers and maintaining customer relationships are top priority and they work to always deliver solutions through this lens
- Ability to learn newer technologies, methodologies, and solutions in the cloud technology space.
- Ability to collaborate across organizational boundaries, build relationships, and achieve broader organizational goals.

Skills Required:

- Agentic AI and Multi-Agent Systems: design review and governance
- Agent Evals, Tracing and Observability
- MCP, Memory and State Management, Context Engineering, RAG
- Python / Java / TypeScript (hands-on)
- Cloud Platform Experience (Azure and/or Google Cloud)
- Engineering Leadership, Hiring and Change Management
- AI Governance, Guardrails, Token and Compute Cost Management

📌 Senior Manager Engineering - AI/Agentic-30271] (Bengaluru)
🏢 Albertsons Companies India
📍 Bengaluru