Senior Backend Engineer, AI Agent

This is a fully remote position, open to applicants in Texas.

📋 Description

• Design, construct, and enhance AI agents utilizing Go/Python within an orchestrator/sub-agent framework.

• Address intent interpretation, task delegation, and secure action execution.

• Take ownership of evaluation-driven development, including the creation of golden datasets, scoring mechanisms, and regression testing suites.

• Monitor essential quality metrics such as discovery recall and accuracy of quotes.

• Develop and fine-tune prompts and model configurations as version-controlled, tested artifacts.

• Integrate agents with MCP servers and backend systems.

• Establish safe tool-call agreements, approval processes for write actions, and safeguards against prompt injection and misuse.

• Equip agents with tracing, metrics, and cost monitoring capabilities.

• Utilize production signals to facilitate quality enhancements.

• Collaborate with product designers and frontend engineers to create conversational experiences.

• Construct proof-of-concept agents to test user stories and enhance them to GA quality standards.

• Influence architectural decisions on complex challenges.

• Guide engineers in best practices for agent engineering.

⛳️ Requirements

• 5+ years of experience in backend or full-stack software development.

• Practical experience in developing agentic AI/LLM applications.

• Preferred minimum of a Bachelor's degree in Computer Science, Electrical Engineering, Software Engineering, Computer Engineering, Management Information Systems; or equivalent experience.

• Strong and demonstrated programming skills in Go, Python, Ruby, or PHP.

• Production experience with LLMs such as Gemini, Anthropic, or OpenAI.

• Experience in creating LLM evaluation datasets, scoring systems/metrics, and leveraging evaluation results to inform iterations.

• Comprehensive understanding of prompt engineering, function/tool invocation, and agent orchestration patterns.

• Extensive experience in designing and developing APIs using gRPC, GraphQL, or REST.

• Experience in system integration of data.

• Practical experience in constructing MCP servers or LLM tool integrations.

• Exceptional problem-solving abilities.

• Strong collaboration and communication skills within cross-functional teams.

• Strong inclination towards execution and delivery.

• Preferred experience with Google ADK, LangChain/LangGraph, Semantic Kernel, or similar agent frameworks.

• Preferred experience with Braintrust, LangSmith, or similar evaluation/observability platforms.

• Preferred experience with RAG systems and refining retrieval quality.

• Preferred experience with e-commerce platforms or SaaS product development.

• Preferred background in conversational AI or natural language processing.

🏝️ Benefits

• Remote-first work environment.

• Optional collaborative workspaces located in Austin, Atlanta, and London.

• Variable compensation options such as bonuses or commissions, when applicable.

• Equity participation, where applicable.

• Benefits aligned with local policies.

• An inclusive and accessible hiring process.

• Government ID and biometric verification process conducted via Persona.