Senior Backend Engineer (AI Agent)

Location: Remote in the United States; optional collaborative workspaces are available in Austin, Atlanta, and London.

Salary: $116,000–$195,000 annual base salary; variable compensation, equity, and benefits may also apply according to local policies.

Company

hirify.global is part of Commerce, a product company building an open, AI-driven commerce ecosystem that includes BigCommerce, hirify.global, and Makeswift.

What you will do

• Design, build, and iterate on conversational AI agents in Go or Python using orchestrator and sub-agent architectures for product discovery, pricing and quoting, order automation, fulfillment, delivery, and post-sale support.
• Own evaluation-driven development by creating golden datasets, scorers, regression suites, and quality metrics such as discovery recall and quote accuracy.
• Develop versioned and tested prompts, model configurations, tool-call contracts, approval flows, and guardrails against prompt injection and abuse.
• Integrate agents with MCP servers, backend tools, and APIs; add tracing, metrics, and cost tracking and use production signals to improve quality.
• Collaborate with product designers and frontend engineers to deliver conversational experiences, rapidly validate user stories, and harden proof-of-concept agents to GA quality.
• Drive architecture decisions on ambiguous problems and mentor engineers in agent engineering practices.

Requirements

• 5+ years of backend or full-stack software development experience, including hands-on experience building agentic AI or LLM applications.
• A preferred minimum Bachelor's degree in Computer Science, Electrical Engineering, Software Engineering, Computer Engineering, or Management Information Systems, or equivalent experience.
• Strong development skills in at least one major language: Go, Python, Ruby, or PHP.
• Production experience with LLMs such as Gemini, Anthropic, or OpenAI.
• Experience building LLM evaluation datasets, defining scorers and metrics, and using evaluation results to drive iteration.
• Strong understanding of prompt engineering, tool or function calling, and agent orchestration patterns.
• Deep experience designing and building APIs with gRPC, GraphQL, or REST and integrating data across systems.
• Hands-on experience building MCP servers or LLM tool integrations.
• Excellent problem-solving, collaboration, and communication skills in a fast-paced, exploratory, cross-functional environment, with a strong preference for execution and delivery.

Nice to have

• Experience with agent frameworks such as Google ADK, LangChain/LangGraph, or Semantic Kernel.
• Experience with evaluation or observability platforms such as Braintrust or LangSmith.
• Experience with RAG systems and retrieval quality tuning.
• Experience with e-commerce platforms or SaaS product development.
• Background in conversational AI or natural language processing.

Culture & Benefits

• Remote-first work environment.
• Optional collaborative workspaces in Austin, Atlanta, and London for gatherings, workshops, and in-person connection.
• Variable compensation, equity, and benefits may be available according to local policies.
• Inclusive and accessible hiring experience with accommodations available on request.
• Interview process includes government ID and biometric verification through Persona.