Principal, Software Engineer - MLE, People.AI

(USA) Bentonville Global Tech AR BENTONVILLE Home Office, United States

Walmart

What’s a career at Walmart or Sam’s Club like? To find out, explore our culture, our opportunities and the difference you can make.

View all jobs at Walmart

Apply now Apply later

Position Summary...

About Walmart

Walmart employs more than 2.3 million associates worldwide, with 1.6 million associates in the U.S. Each year, Walmart hires 500,000 applicants to fill thousands of job profiles from engineers, designers, and marketers to pilots and buyers. We promote over 300,000 people annually to positions of greater responsibility.

About People Technology Team

The Enterprise People Technology team supports the successful deployment and adoption of new People technology across the enterprise. As a Fortune #1 company, our work impacts millions of associates globally. We strive to continuously improve people technology and products to help managers and associates focus on what matters most - supporting our customers and members. People Technology is a significant segment of Walmart Global Tech’s Enterprise Business Services, invested in building a compact, robust organization that includes service operations and technology solutions for Finance, People, and the Associate Digital Experience.

About People.AI Team

The People.AI team is responsible for developing and deploying AI/ML solutions supporting the Walmart associates globally. In this role, you will build an LLM-powered intelligent experience within a chatbot or business application to enhance associate experience and productivity. You will design and build an intelligent conversational interface that improves communication, automates tasks, accesses data and insights, and provides personalized Q&A support to associates, ultimately creating a more efficient and engaging work environment.

What you'll do...

About the Role:

We are looking for a Principal Software Engineer who is an architect-level expert in Python, with a deep mastery of LLM-driven systems, agentic architectures, and scalable intelligent automation. This is a pivotal role where you'll define the technical strategy, influence architecture across domains, and lead the creation of next-gen AI-driven platforms that move beyond prompt engineering into modular reasoning systems.

This role isn’t about building one-off workflows—it’s about inventing and hardening intelligent systems that can reason, act, and adapt. You will shape the core architecture of multi-agent platforms, ensure LLM integrations are secure, efficient, and observable, and build frameworks that others can extend across use cases and orgs.

As a Principal Engineer, you set the vision, write the critical path code, guide Staff and Senior engineers, and are the final word on whether a design is ready for scale.

Key Responsibilities:

Define and own the agentic architecture strategy across teams, including MasterAgent design, tool orchestration, memory layers, and dynamic router agents.

Architect modular, testable, and composable Python systems that support multi-agent workflows, tool-chaining, RAG, memory management, and fallback strategies.

Design LLM-powered execution engines that support both high throughput and adaptive reasoning (via LangChain, AutoGen, or custom frameworks).

Lead implementation of retrieval-augmented generation (RAG) pipelines, semantic search, and structured knowledge memory systems.

Build and scale integrations with internal LLMs, including handling signature-based auth, function calling, and context management at scale.

Drive end-to-end lifecycle: from configuration schema (YAML) to execution trace logging, observability, and self-healing recovery patterns.

Lead cross-org architecture reviews, influence roadmap prioritization, and set coding and design standards for all agentic platform work.

Act as a multiplier by mentoring Staff/Senior engineers, building reusable libraries, and leading technical guilds around AI agent infrastructure.

Must-Have Qualifications:

10+ years of professional software engineering experience, with 7+ years in Python, building distributed systems at scale.

Deep knowledge of agentic design patterns, including:

ReAct, Plan-and-Execute, AutoGen-style coordination

Tool calling, dynamic agent routing, and recursive agent planning

Semantic memory, embedding-based context lookup, summarization windows

Expertise in building LLM-based systems with LangChain, OpenAI, Anthropic, or custom orchestrators.

Hands-on experience with:

RAG pipelines using vector stores (FAISS, Pinecone, Weaviate, Qdrant, Azure Cognitive Search)

LLM evaluation and observability (tracing, token usage, agent state tracking)

Workflow orchestration using config-first approaches (YAML/JSON definitions, step runners, etc.)

Proven ability to drive technical vision, resolve ambiguity, and make architectural tradeoffs at scale.

Strong background in distributed systems, task queues, asynchronous workflows, and backend performance optimization.

Experience in cloud-native environments (AWS, GCP, or Azure), including containerization, monitoring, and secure API integrations.

 

Nice-to-Have:

Built or contributed to a custom agentic orchestration framework used across multiple product lines.

Experience with vector search optimization, context ranking, or temporal memory solutions.

Published talks, blogs, or papers on LLM systems, AI architecture, or applied reasoning frameworks.

Deep understanding of how to apply LLM systems in regulated or high-compliance environments (PII handling, redaction, observability).

Exposure to DevEx platforms for developers to build workflows on top of intelligent agents.

Familiarity with multi-modal agents (text + vision), LLM simulation patterns, or offline evaluation loops.

 

What Success Looks Like:

You’ve built an agent platform that others across the org use as the foundation for intelligent automation.

You turn abstract ideas into clean, extensible, production-grade Python systems that scale and evolve.

You elevate technical conversations, coach Staff+ engineers, and are the go-to person for unblocking complex challenges.

You are not just LLM-aware—you pioneer how LLMs are applied in production systems, with a clear perspective on what's reliable, efficient, and future-proof.

Your influence goes beyond code—you shape tech culture, architectural direction, and platform vision.

At Walmart, we offer competitive pay as well as performance-based bonus awards and other great benefits for a happier mind, body, and wallet. Health benefits include medical, vision and dental coverage. Financial benefits include 401(k), stock purchase and company-paid life insurance. Paid time off benefits include PTO (including sick leave), parental leave, family care leave, bereavement, jury duty, and voting. Other benefits include short-term and long-term disability, company discounts, Military Leave Pay, adoption and surrogacy expense reimbursement, and more.

‎ 

‎ 

‎ 

You will also receive PTO and/or PPTO that can be used for vacation, sick leave, holidays, or other purposes. The amount you receive depends on your job classification and length of employment. It will meet or exceed the requirements of paid sick leave laws, where applicable.

‎ 

For information about PTO, see https://one.walmart.com/notices.

‎ 

‎ 

Live Better U is a Walmart-paid education benefit program for full-time and part-time associates in Walmart and Sam's Club facilities. Programs range from high school completion to bachelor's degrees, including English Language Learning and short-form certificates. Tuition, books, and fees are completely paid for by Walmart.

‎ 

Eligibility requirements apply to some benefits and may depend on your job classification and length of employment. Benefits are subject to change and may be subject to a specific plan or program terms.

‎ 

For information about benefits and eligibility, see One.Walmart.

‎ 

The annual salary range for this position is $110,000.00-$220,000.00

‎ 

Additional compensation includes annual or quarterly performance bonuses.

‎ 

Additional compensation for certain positions may also include:

‎ 

‎ 

- Stock

‎ 

‎ 

Minimum Qualifications...

Outlined below are the required minimum qualifications for this position. If none are listed, there are no minimum qualifications.

Option 1: Bachelor's degree in computer science, computer engineering, computer information systems, software engineering, or related area and5 years’ experience in software engineering or related area.
Option 2: 7 years’ experience in software engineering or related area.

Preferred Qualifications...

Outlined below are the optional preferred qualifications for this position. If none are listed, there are no preferred qualifications.

Master’s degree in computer science, computer engineering, computer information systems, software engineering, or related area and 3 years' experience in software engineering or related area., We value candidates with a background in creating inclusive digital experiences, demonstrating knowledge in implementing Web Content Accessibility Guidelines (WCAG) 2.2 AA standards, assistive technologies, and integrating digital accessibility seamlessly. The ideal candidate would have knowledge of accessibility best practices and join us as we continue to create accessible products and services following Walmart’s accessibility standards and guidelines for supporting an inclusive culture.

Primary Location...

2501 Se J St, Ste A, Bentonville, AR 72716-3724, United States of America
Apply now Apply later
Job stats:  0  0  0

Tags: Anthropic APIs Architecture AWS Azure Chatbots Classification Computer Science Distributed Systems Engineering FAISS Finance GCP Generative AI JSON LangChain LLMs Machine Learning OpenAI Pinecone Pipelines Prompt engineering Python RAG React Weaviate

Perks/benefits: Career development Competitive pay Equity / stock options Health care Insurance Medical leave Parental leave Salary bonus

Region: North America
Country: United States

More jobs like this