• To own the soul of our chatbot experience and transform our automated support from a "barrier" into a premium "Resolution Engine." • Ensure that every interaction a customer has with our brand is intuitive, helpful, and trustworthy • Design the seamless transition from "Bot to Human" • Use A/B testing to refine bot responses • Implement "Validation Loops" so the bot confirms it understands the user before acting • Establish strict protocols and guardrails to ensure the LLM remains within brand voice • Identify which manual 1-on-1 human tasks can be safely automated • Work with Support, Product, and engineering to ensure the bot’s knowledge base is synced

Description: SPS Commerce is a leading provider of cloud-based supply chain management solutions, serving a global network of retail trading partners. We foster a collaborative and inclusive work environment where innovation and continuous improvement are highly valued. Join SPS Commerce and be part of a dynamic team that's transforming the global retail supply chain! Position Summary: Join the team that is redefining the global supply chain. At SPS Commerce, we aren’t just adding a chatbot; we are building MAX, the world’s first agentic supply chain network. Leveraging 25 years of proprietary intelligence and billions of transactions, the MAX AI team is moving beyond simple dashboards to create autonomous agents that understand business intent and context. As a Senior AI Engineer, you will architect the RAG pipelines and AI Agents that power MAX Chat, Monitor, and Connect. You’ll work at the bleeding edge of the Model Context Protocol (MCP) to ensure our agents collaborate seamlessly across the retail ecosystem. If you want to lead the "Great Rewiring of Trade" and build secure, scalable AI that solves real-world logistics challenges this is your seat at the table. Key Responsibilities: - AI Orchestration & Agents: Design multi-step AI agents that don't just "talk" but take action, integrating external tools and APIs to resolve complex user requests end-to-end. - Prompt Engineering: Write and maintain structured system prompts that keep model behavior predictable and within expected boundaries. - Build and improve RAG pipelines: Develop and tune retrieval pipelines using vector search, reranking, and contextual compression to keep responses accurate and grounded. - Drive observability with LangSmith: Setting up observability and evaluation infrastructure to monitor for bias, latency spikes, and cost-per-request. - Harden the system against AI-specific threats: Identify and mitigate risks like prompt injection and context manipulation as part of normal engineering practice — not an afterthought. - Grow and share AI expertise: Stay current on LLM techniques and actively contribute to the team's shared knowledge. Location:  Preference is in our Minneapolis office but it is also available as a fully remote role across the US Required Qualifications: - A Bachelor’s degree plus 5 years of software development experience; a Master’s Degree plus 3 years of experience; a PhD without prior experience; or equivalent education and work experience - Proficiency in React and at least one backend language (preferably Python or JavaScript/TypeScript). Must be language-agnostic and willing to learn new stacks. - Experience with Langsmith or similar AI observability/troubleshooting tools (e.g., AWS observability). - Experience with RAG (Retrieval-Augmented Generation) pipelines, vector databases, and building/scaling AI Agents. - Familiarity with MCP (Model Context Protocol), Claude Code, and AI-assisted development tools (Co-pilot). - Hands-on experience with Kubernetes (K8s) and AWS (S3, Bedrock). - Strong understanding of Containerization. - Understanding of LLM-specific vulnerabilities, such as prompt injection and context-risk management. - Version Control: Git What We Offer: At SPS Commerce, we are committed to ensuring that each employee's compensation reflects their unique experiences, performance, and skills in their role. The salary range for this role considers several factors, including education, relevant skills, work history, certifications, location, and more. The annual salary range for this role is: $86,600 - $130,000 USD Annual. The actual salary offered will be determined based on the factors listed above and may fall anywhere within the range. SPS Commerce offers a comprehensive benefits package designed to support employees’ health, well-being, and financial security. Benefits are country-specific and aligned with local laws and market practices. Commitment to our Employees: At SPS we power connections that drive the world of commerce forward, and our success depends on making strong decisions, fostering innovation, delivering unparalleled customer solutions, and driving outstanding business performance. We achieve this by creating an environment where every employee feels a true sense of belonging. We embrace diversity, equity, and inclusion, ensuring everyone feels accepted, valued, and empowered to make a meaningful impact. We are committed to affirmative action and equal opportunity in all aspects of employment. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, or status as a protected veteran.

• Collaborate with the CTO, AI consultant, and development team to design and deploy robust, scalable AI/ML architectures • Develop, train, and maintain AI models, data pipelines, and integrations with APIs, databases, and SaaS platforms • Experiment with new LLMs, embeddings, vector databases, and orchestration frameworks (e.g., LangChain, Semantic Kernel, or similar) • Lead hands-on development/ prototyping of LLM-based applications, intelligent agents, and automation workflows • Define AI architecture standards, establish model governance, and contribute to the long-term AI strategy in collaboration with the CTO • Partner with business and technical leaders to translate strategic AI goals into actionable engineering initiatives • Design systems for high availability, scalability, and efficient deployment in cloud environments (Azure, AWS, or GCP) • Create technical documentation, architecture diagrams, and playbooks for deployment and scaling of AI solutions • Participate in code reviews, mentor junior developers, and foster a culture of innovation and excellence in AI engineering • Stay at the forefront of emerging AI frameworks, APIs, and tools, bringing forward practical innovations to enhance our products and systems

• Build and ship AI-enabled automation that improves scalability, reliability, and cost-to-serve across MoonTech workflows. • Design, implement, and own production services for AI features — APIs, orchestration, background jobs, and monitoring. • Build full-stack product surfaces for internal tools and user-facing automation, including clean UX, resilient backend logic, and secure data handling. • Partner with Product, Data, and Engineering to translate business workflows into automated systems with clear success metrics. • Implement evaluation and quality loops for AI features, including test datasets, online measurement, and feedback-driven iteration. • Integrate with third-party systems and internal services (payments, CRM, attribution/analytics, messaging, partner platforms) to automate end-to-end journeys. • Establish operational excellence for AI workflows: observability, incident readiness, cost controls, rate limiting, and reliability safeguards. • Contribute to platform standards around data privacy, access control, and safe deployment patterns. • Shape AI use cases in partnership with Product and Engineering, and measure impact through clear evaluation metrics. • Use AI tools and automation in your own day-to-day work to streamline analysis, documentation, and planning.