Staff AI Full-Stack Engineer (Remote)

About the RoleAs Staff Software Engineer, you will be part of a dynamic, cross-functional team dedicated to enhancing the customer experience. You will collaborate closely with Design, Product Management, and Engineering experts to tackle real-world challenges and deliver innovative solutions that elevate our retail offerings.What You’ll DoLead the development of high-quality applications that are robust, observable and measurable. Using extreme programming (XP) practices and a user-centric approachNavigate the entire application lifecycle in collaboration with designers, product managers, and other engineers on the product teamLeverage critical thinking, lead lean experimentation and influence decisions backed by data and industry best practices to implement desired business outcomesEstablish and lead product engineering and software standards and continuously elevate existing standards using the new ones in the industry Mentor junior team members in pairing sessions, one-on-ones and ad-hoc as the need arises, and create teachable momentsContribute to cultural transformation by modeling partnership, collaboration, and technical initiatives and giving and receiving feedback regularly both within the team and across the organizationChampion XP practice and knows when to customize it for effectiveness and also engages in conversations around practice, processes and communityAdditional tasks may be assignedAddendumSTAFF AI SOFTWARE ENGINEERDesign and build modular, headless AI backend services, advanced RAG architectures, and multi-agent orchestration workflows (e.g., LangChain, AutoGen, CrewAI).Construct enterprise-grade Model Context Protocol (MCP) gateways, Application Programming Interface (API) integration/mediation layers, rate limiters, and security proxies that allow autonomous agents to safely read and write to enterprise systems.Develop lightweight, streaming simulation frontends ("Dry-Run" interfaces) solely to validate agent behaviors, prompt strategies, and human-in-the-loop workflows during pilot discovery.Collaborate with Applied/Data Science and Machine Learning specialists to fine-tune Small Language Models (SLMs), execute weight quantization (AWQ/GPTQ), and optimize GPU memory utilization for high-throughput inference.Instrument distributed tracing, token utilization logging, and inference latency telemetry across the AI stack.Package reusable code libraries, containerized microservices, and integration SDKs for domain delivery and implementation teams.Architect resilient Compound AI Systems that orchestrate dynamic routing between deterministic APIs, specialized SLMs, and frontier LLMs.Requirements6+ years of demonstrated experience building and scaling production applications using foundation models, RAG, or agentic workflows6+ years of experience integrating AI applications securely with enterprise data, APIs, and identity/access controls4+ years of experience evaluating and optimizing AI application quality, latency, reliability, and costWhat Skills You HaveRequired6+ years of experience in software developmentProven ability to manage multiple competing prioritiesAdvanced knowledge of application design patterns, event-driven architecture, database schemas, and testing strategiesExperience with large-scale application troubleshooting and performance tuningDemonstrated experience working with major cloud platforms (GCP, AWS, or Azure)Knowledge and experience with continuous integration, continuous deployment, and test-driven developmentPreferredBachelor's Degree or equivalent in MIS, Computer Science or related fieldFamiliarity and experieJob SummaryJob number: R503701Profession: Technology