Agent Engineer

Here at Scotts Miracle-Gro there is no such thing as a typical day. Our culture is constantly energized by new and exciting growth opportunities and at a rapid pace. Below are details on an open job. If the role interests you and you would like to be considered we encourage you to apply!

Agent Engineer Role Summary
You will own the AI agent development lifecycle at Scotts Miracle-Gro - from pilot through deployment and continuous iteration. Using platforms like Sierra and modern agent frameworks, you will design and deliver production-grade AI agents that solve real business challenges: customer service, commerce, internal workflows, and cross-functional automation. You are joining SMG to become our in-house expert who learns, configures, and extends agent platforms to drive measurable outcomes for our brands and consumers.

In this role you will:
Agent Development Lifecycle (ADLC):

• Own end-to-end agent development - from requirements and design through pilot, deployment, monitoring, and iterative improvement.
• Build production-grade AI agents using Sierra and complementary tools (Lang Chain, ADK, or similar orchestration frameworks) for customer-facing and internal use cases.
• Design agent architectures: conversation flows, tool use, RAG integration, human handoff logic, and multi-channel deployment (chat, SMS, voice, email).
• Implement prompt engineering, guardrails, and evaluation pipelines to ensure agents meet quality, safety, and brand standards.

Platform Mastery and Technical Leadership:

• Become the in-house expert on Sierra and related agent platforms - learn the Agent SDK, Agent Studio, and deployment options to maximize platform value.
• Evaluate when to use platform-native capabilities vs. custom extensions; recommend build vs. buy vs. configure for new agent use cases.
• Integrate agents with SMG systems: CRM, e-commerce, knowledge bases, and internal tools. Ensure secure, compliant access to data and APIs.
• Establish reusable patterns, templates, and best practices for agent development that the CoE and FDEs can leverage.

Cross-Functional Delivery:

• Partner with Digital and CS teams to identify high-value agent opportunities and define success metrics.
• Track agent performance (resolution rates, satisfaction, deflection, latency) and drive continuous improvement based on data and user feedback.
• Document agent designs, runbooks, and operational procedures. Support responsible AI practices and governance requirements.

What you'll need to be successful:
Required:

• Bachelor's or Master's degree in Computer Science, Software Engineering, or a related technical field.
• 3+ years of software engineering experience, with 1+ years building or integrating AI/LLM-powered applications or agents.
• Strong programming fundamentals - Python required; experience with React, Type Script/JavaScript and API design is a plus.
• Hands-on experience with generative AI: LLMs (GPT-4, Claude, Gemini), prompt engineering, RAG, vector databases, and agent orchestration (Lang Chain, Flowise, or similar).
• Ability to learn new platforms quickly - you will ramp on Sierra (or equivalent) and become productive within weeks.
• Track record of shipping production software with clear ownership of design, implementation, and iteration.
• Clear communicator who can explain technical decisions to non-technical stakeholders and align on priorities.

Preferred:

• Experience with Sierra, Voice AI, or other enterprise conversational AI platforms.
• Familiarity with customer service, e-commerce, or CPG/retail domains.
• Experience with cloud platforms (GCP, AWS, or Azure) and CI/CD for ML or agent deployments.
• Exposure to agent evaluation, A/B testing, or observability for AI systems.
• Understanding of responsible AI, data governance, and compliance considerations for customer-facing AI.

How this role connects to our AI vision:
The AI CoE delivers value through a combination of strategy, platform expertise, and forward-deployed execution. The Agent Engineer is the platform specialist - the person who owns the agent stack, learns the tools deeply, and ensures SMG can reliably build and operate AI agents  enable the FDEs and business units to deploy agents with confidence, while you focus on the technical depth required to make those agents production-ready and continuously improving.

The starting budgeted pay range for this role will generally fall between $ - $ per year. Scotts will consider various factors in determining the actual pay including your skills, qualifications, experience, and geographical  addition to the determined base salary, this role is also incentive eligible under our corporate bonus programs.

For remote roles where the final candidate resides in Alaska, California, Colorado, Illinois, New York, Oregon or Washington, state required pay thresholds will be factored into base salary.

Here at Scotts Miracle-Gro, we believe providing an enriching and engaging employee experience is what sets us apart from other organizations. We recognize our employees are so much more than just their…