We are excited to announce an opening for Senior Engineering Manager, AI-SDLC at Albertsons. Please find below the details of the role and its responsibilities.

Skills Required: Gen AI, Agentic AI, Autonomous Software Engineering, Machine Learning, Artificial Intelligence

Experience Range: 12 15 years

Job Title: Sr. Manager AI-SDLC (Autonomous Software Engineering Platform)

Role Overview:

The Sr. Manager AI-SDLC will lead the design, engineering, and rollout of Albertsons' next-generation AI-driven Software Development Lifecycle (AI-SDLC) platform a system where autonomous AI agents plan, write, test, review, and ship software collaboratively with human engineers in the loop.

This role is pivotal in reimagining how Albertsons builds software: shifting from developers writing every line of code to developers directing, reviewing, and governing fleets of autonomous coding agents that handle requirements analysis, code generation, testing, code review, deployment, and incident triage with humans retaining control at critical decision points.

You will lead an engineering team responsible for architecting and operationalizing platform components including agent orchestration for the SDLC, autonomous coding/testing agents, human-in-the-loop approval workflows, code-quality and safety guardrails, CI/CD integration, and developer experience tooling that lets engineering teams safely delegate work to AI agents.

This is a hands-on leadership role ideal for someone who has built agentic AI platforms, developer tooling, or autonomous automation systems in large enterprises or high-velocity startup environments, and who is excited to redefine how software gets built.

Key Responsibilities:

Platform Architecture & Engineering:

- Lead end-to-end design and engineering of Albertsons' AI-SDLC platform, enabling autonomous, semi-autonomous, and human-in-the-loop software delivery workflows.
- Architect core components including:
- Agent orchestration layers for the software development lifecycle (planning, coding, testing, review, deployment) using LangChain, LangGraph, OpenAI Assistants, or similar frameworks.
- Autonomous coding and testing agent frameworks (e.g., patterns similar to OpenGPTs, n8n workflows) capable of executing multi-step engineering tasks.
- Human-in-the-loop checkpoints and approval gates that let engineers review, correct, and approve agent-generated code, tests,



and deployments before they progress.
- Vector databases (FAISS, Pinecone, Weaviate, Chroma, pgvector) for codebase retrieval, context grounding, and RAG over internal engineering knowledge.
- Prompt engineering libraries, reusable agent tools, code-review templates, and evaluation harnesses to measure agent code quality.
- Secure tool/function calling into source control, CI/CD, and cloud infrastructure, with policy-as-code and responsible AI guardrails.
- Build scalable APIs, SDKs, and services that make autonomous SDLC capabilities reusable across engineering and product teams.

Team Leadership:

- Lead, mentor, and grow a team of AI platform engineers, LLM engineers, MLOps engineers, and agentic workflow developers building the AI-SDLC platform.
- Establish engineering best practices, code quality standards, and DevOps processes for AI-authored and AI-assisted software.

Innovation & Architecture:

- Evaluate and integrate emerging open-source technologies (e.g., LangChain, LangSmith, LlamaIndex, Dust, n8n, OpenGPTs, Haystack) for autonomous software engineering use cases.
- Drive architectural decisions for multi-model support (OpenAI, Anthropic, Gemini, Mistral, Llama) across coding, testing, and review agents.
- Partner with Data Engineering, Cloud Infra, Security, and Digital Product teams to ensure the AI-SDLC platform integrates seamlessly with existing engineering toolchains (source control, CI/CD, ticketing).

Platform Operations & Governance:

- Implement governance, compliance, and auditability mechanisms so every autonomous agent action in the SDLC is traceable, reviewable, and reversible by a human.
- Design human-in-the-loop review and escalation policies that balance developer velocity with code quality, security, and risk controls.
- Oversee observability, telemetry, monitoring, and cost optimization for agentic workloads across the development lifecycle.
- Ensure high availability, performance, and secure access controls (SSO, RBAC, secrets management) for agents operating on production codebases.





Cross-Functional Collaboration:

- Work closely with product managers, engineering leaders, Data Science, AI Research, and Engineering teams to enable rapid adoption of autonomous development workflows.
- Partner with the AI Governance Council to operationalize safety, privacy, ethical AI, and model explainability for AI-generated code (interpretability tools, etc.).

Execution & Delivery:

- Translate the AI-SDLC vision autonomous agents building software with humans in the loop into concrete platform features and a delivery roadmap.
- Deliver iterative platform increments with measurable impact on developer productivity, code quality, and delivery speed.
- Ensure successful rollout, adoption, and developer onboarding for autonomous AI-SDLC tooling across the enterprise.

Required Qualifications:

- 12+ years of total experience in software engineering, developer platform engineering, or large-scale distributed systems.
- 35+ years of hands-on experience building GenAI or LLM-based systems, agentic frameworks, or autonomous software engineering / developer tooling platforms.

Solid expertise in:

- Python, TypeScript/Node.js, FastAPI, microservices.
- LangChain, LangGraph, LlamaIndex, OpenAI function calling, agent orchestration frameworks.
- Workflow automation engines (n8n, Temporal, Airflow) or agent orchestration tools applied to CI/CD and SDLC automation.
- Vector DBs: FAISS, Pinecone, Milvus, Chroma, Weaviate.
- Cloud platforms: GCP, Azure, or AWS with AI/ML stack experience.
- Software engineering fundamentals: source control (Git), CI/CD pipelines, automated testing, and code review practices essential for designing agents that operate safely within them.
- Solid experience with MLOps / LLMOps: CI/CD for models, evaluation, monitoring, prompt versioning.
- Experience designing human-in-the-loop systems, approval workflows, or safety guardrails for autonomous/agentic systems.
- Experience handling system performance, cost management, and scaling LLM/agentic workloads.
- Proven leadership experience in managing high-performance engineering teams.

Nice to Have:

- Prior experience building or rolling out internal developer tools / platform engineering teams.
- Familiarity with AI code-review, AI testing, or AI code-generation tools (e.g., GitHub Copilot Workspace, Devin, Cursor, SWE-agent style systems).

📌 Senior Manager Engineering (Bengaluru)
🏢 Albertsons Companies India
📍 Bengaluru