The Opportunity:Walmart's Supply Chain AI Lab & Innovation Factory is building a new generation of production-grade agentic AI systems that reason over complex enterprise information, coordinate specialized agents, use tools safely, plan and execute long-horizon work, and continuously improve through rigorous evaluation and model post-training. This role exists to build those systems end to end-and to improve the models that power them.
This is not an analytics-focused data science role. It is a deeply hands-on AI systems engineering position focused on designing, building, and operating production software.
As the Distinguished technical leader in this space, you own production systems end to end across the full technology stack-agent orchestration and model logic, backend services and APIs, the data layer, and web and CLI/TUI interfaces. Through exceptional judgment, practical invention, mentoring, and code, you set technical direction and shape the architecture of the shared agentic platform and its model-improvement system.
What you will build and own: Build advanced agentic systems end to end - Own the architecture, implementation, evaluation, launch, and operation of complex, autonomous multi-agent applications that tackle our highest-value enterprise initiatives-from the first working full-stack proof of concept through dependable, production-scale service.
- Build systems in which specialized agents can reason, plan across long horizons, coordinate work, use tools, retrieve enterprise knowledge, maintain secure and durable session and workflow state, manage context growth, ask for human approval when needed, and cancel, resume, replay, or recover safely from failure.
- Build a policy-first agent runtime and control plane with deterministic allow, deny, and ask decisions; least-privilege tool and data access; scoped identity and authorization; auditable human approvals; bounded subagent delegation; and safe cancellation, user steering, and retry behavior for long-running work.
- Own the full product path as a full-stack systems engineer: agent and model logic, backend services and APIs, the data layer (database and schema design, data modeling, migrations, and data integrations), telemetry, monitoring, and thoughtful React/TypeScript experiences for associates and operators. Where the workflow demands it, design equally usable AI-native CLI/TUI or headless, structured-output interfaces that support automation, operations, and CI/CD-style integration.
Where you will apply this These capabilities will first be applied to some of Walmart's most complex operational and supply-chain problems, beginning with the Autonomous Supply Chain Engine and its Discovery Loop-a continuous, human-in-the-loop mechanism that monitors signals, discovers opportunities and risks, reasons through changing conditions, and generates strategic recommendations.
- Build and own the Discovery Loop within our Autonomous Supply Chain Engine. This is the flagship capability this role exists to build: you will own its execution model, its knowledge and context layer, its evaluation loop, and the learning path that turns human feedback and business outcomes into measurable improvement.
- Partner directly with supply chain experts, scientists, data owners, operations, and engineering stakeholders to discover the real workflow, prototype rapidly with real users, measure value and risk, and harden successful solutions without losing speed.
This is a high-visibility builder role. You will work closely with the SVP of Supply Chain Strategy, the head of AI for Supply Chain Strategy, and senior leaders across supply chain strategy, operations, data, and technology-bringing grounded technical insight to strategic priorities and turning them into responsibly operated products. Visibility here is earned through working software, sound judgment, clear communication, and measurable outcomes.
Prior supply chain or logistics experience is not required. We will help you learn the operational domain; you bring outstanding depth in agentic AI engineering, software engineering, and machine learning engineering, plus the curiosity and ownership to turn unfamiliar problems into durable products.
Engineer the agentic AI foundation - Own the design and build of advanced multi-agent harnesses, runtimes, and orchestration capabilities using frameworks such as Pydantic AI, LangGraph, LangChain, AutoGen, or LlamaIndex, or purpose-built custom infrastructure. Building your own runtime where that is the right call is a strength, not a gap. Establish typed contracts, testability, scalability, operability, and developer ergonomics as non-negotiable platform properties.
- Engineer explicit, inspectable agent execution. Design graph-based, state-machine-based, event-driven, planner/executor, or equivalent execution models as the problem warrants, with explicit state, typed dependencies and handoffs, conditional branching, fan-out and fan-in to subagents, retry and repair paths, loop detection, cost and time budgets, and hard termination conditions. Design external verification into the system-test runners, execution results, transaction outcomes, deterministic checks, and expert human review-because a model reviewing its own output is not verification.
- Build governed knowledge and context infrastructure for durable agent memory. Choose and combine the right representations-knowledge and context graphs, vector retrieval, relational and temporal models, or hybrids-with an explicit schema and ontology treated as a product contract. Own entity resolution and conflict handling, construction and enrichment pipelines from structured and unstructured sources, provenance and temporal validity, schema validation and evolution, and multi-hop retrieval that answers questions flat retrieval cannot.
- Build and operate agent skills, tool adapters, hooks and extension points, Model Context Protocol (MCP) clients and servers, structured outputs, function calling, enterprise APIs, identity, and secrets management. Own MCP lifecycle and reliability end to end: secure configuration and authentication, per-agent tool binding, schema compatibility, tool discovery, timeouts, health monitoring, retries, circuit breaking, quarantine, cleanup, failure isolation, and auditable operations.
- Create governed extension ecosystems for agents, skills, commands, plugins, hooks, tool adapters, and reusable workflows. Define stable contracts, compatibility and versioning strategies, secure installation and update paths, isolation boundaries, rollback behavior, and observability so extensibility does not become an uncontrolled code-execution surface.
- Treat agent quality as an engineering discipline: golden tasks, offline benchmarks, online experiments, adversarial and regression testing, failure analysis, measurable quality thresholds, and release gates.
- Establish practical AgentOps / LLMOps practices for prompt and tool versioning, tracing, evaluation datasets, workflow reliability, cost and latency controls, incident learning, and continuous improvement of long-running autonomous systems. Instrument the system so engineers and operators can answer, with evidence, what the agent did, why it was permitted, which model, tool, and policy version was involved, what data and integrations were used, what it cost, where it failed, and how to reproduce or remediate the outcome safely.
Advance the models themselves - Improve model reasoning and quality through hands-on post-training: reinforcement learning (RLHF/RLAIF), preference optimization, supervised fine-tuning, distillation, and reward and grader design to improve reasoning, tool-use reliability, and domain-specialized behavior across frontier models and smaller, domain-specialized models.
- Build the model-improvement flywheel. Turn production interaction traces, tool-use trajectories, human feedback, and successful and failed reasoning paths-together with Walmart's proprietary enterprise and operational data, synthetic data, and curated evaluation sets-into governed training and evaluation datasets. Use them to post-train, distill, evaluate, and redeploy increasingly capable domain-specialized models back into the agentic systems, so the platform you build continuously improves the models that power it. Own the data governance, provenance, privacy, and access controls that make this safe at enterprise scale.
- Design provider-aware, model-agnostic execution and routing layers that account for model capabilities-including multimodal inputs and outputs across text, images, and documents-context limits, structured outputs, streaming behavior, credentials, rate limits, transient failures, and explicit quality, latency, and cost trade-offs.
Make every solution safe, scalable, and production-ready - Design systems on Google Cloud Platform (GCP) and Walmart internal technologies that are secure, fault tolerant, cost-aware, observable, highly available, and low latency.
- Build responsible enterprise-agent behavior through least-privilege access, explicit authorization boundaries, complete audit trails, data-protection controls, defenses against prompt injection and untrusted instructions, approval controls for consequential actions, and reversible recovery paths.
- Design distributed data, streaming, and telemetry systems using technologies such as Kafka, Flink, Spark, OpenTelemetry, and Grafana; use operational signals to improve product quality, reliability, and user trust.
- Set quality, performance, and release standards with layered unit, integration, API, workflow, and user-journey testing; adversarial safety testing; benchmark- and profile-driven performance work; CI/CD quality gates; reliable rollout and rollback practices; and incident-response readiness.
- Deliver accessible associate-facing experiences that meet applicable Walmart accessibility standards, including WCAG 2.2 AA where applicable.
Lead by building and raising the bar - Set a multi-year technical direction for shared agent foundations and the products built on them while staying hands-on-owning architecture, critical-path code, technical spikes, design reviews, and production incidents.
- Raise the engineering bar through clear technical writing, rigorous code and architecture reviews, reusable platform capabilities, and hands-on mentoring of Principal, Staff, and senior engineers.
- Make consequential technical trade-offs based on evidence, security, maintainability, measurable outcomes, and user needs-not novelty for novelty's sake.
- Turn ambitious ideas into responsibly operated products through high standards, constructive collaboration, direct communication, and relentless follow-through.
The bar for this role We are hiring for impact that reaches well beyond the boundaries of a single role. Delivering strongly against your own responsibilities is the starting point for this position, not the measure of success. At the Distinguished level we expect you to change what the organization is able to build and the speed and confidence with which it can build it.
In practice, that means raising the technical performance of the engineers and teams around you, creating capability that did not previously exist rather than only operating what does, taking ownership of the most consequential and least well-defined problems before anyone assigns them, and leaving behind architectures, standards, and reusable foundations that continue to compound long after any single project ships.
What you will bring - 10+ years of hands-on software engineering and architecture experience; 12+ years preferred. Demonstrated Distinguished, Fellow, Principal, Senior Staff, or equivalent scope: you have led difficult technical work across organizations and taken direct, hands-on ownership of shipping and operating complex systems.
- Exceptional end-to-end builder ownership. You are capable of personally building the critical path of a frontier-grade, full-stack agentic platform end to end-agent runtime, CLI/TUI, web frontend, backend services and APIs, and the underlying data layer-while creating leverage for the engineers building alongside you. You can take an ambiguous operational problem from first principles to a working prototype, make the trade-offs clear, earn stakeholder trust, and do the unglamorous hardening required to run a reliable production service.
- Co-equal depth in agentic AI engineering, software engineering, and machine learning engineering: ML and LLM fundamentals, experimental design, retrieval and ranking, model evaluation, production trade-offs, and sound judgment about when an LLM is not the right solution.
- Deep, hands-on experience with model post-training-reinforcement learning (RLHF/RLAIF), preference optimization, supervised fine-tuning, distillation, and reward and grader design-applied to improve reasoning, tool-use reliability, and domain-specialized model behavior, including creating smaller domain-specialized models.
- Deep production experience with stateful, policy-controlled agent runtimes and tool-using multi-agent systems for autonomous long-horizon work: durable session lifecycle, context-window management, retrieval and RAG, guardrails, evaluation systems, secure delegation, safe tool use, interruption handling, and recovery-built on established orchestration frameworks or on custom infrastructure of your own design, including MCP and production tool and integration lifecycle management.
- Broad applied ML depth across several areas such as reinforcement learning, multimodal modeling, retrieval and ranking, forecasting, optimization and operations research, experimentation, or model evaluation-together with production ML lifecycle and MLOps practices, and judgment about when a classical model beats an LLM.
- Expert Python plus strong production backend capability in one or more of Go, Java, or TypeScript, with true full-stack capability across React/TypeScript frontend, APIs, and the data layer.
- Demonstrated depth in distributed systems and production reliability, including streaming and batch platforms, Kubernetes/Docker, CI/CD, telemetry and observability, SLOs/SLIs, availability, latency and cost management, secure enterprise integrations, incident learning, and layered testing.
- Deep fluency with AI-native software-development workflows and coding agents such as Claude Code, Codex, Cursor, Copilot, or equivalent tools, applied with rigorous engineering judgment, code review, evaluation, and testing.
