AI Software Lead

About the Role

This role is not a traditional software engineering position. You will lead agent‑driven software delivery: deciding what to build, decomposing work for AI coding agents, supervising their output, validating quality, and owning what ships. Your performance will be measured by the reliability, maintainability, and production readiness of the software produced by AI agents, not by how many lines of code you write.

You will operate AI coding agents—such as Claude Code, Codex, Cursor, and successor tools—primarily for software production. Your value lies in setting clear constraints, judging when output is incorrect, and proving that results are correct. A key part of your role is building the scaffolding around agent‑driven development: project context, tests, architectural rules, file conventions, allowed dependencies, review checkpoints, and patterns that reduce drift over time.

• Translate business problems into clear specifications, constraints, and implementation plans for AI coding agents.
• Direct AI coding agents to design, build, test, and ship applications, workflows, and AI‑enabled tools.
• Decompose ambiguous requests into agent‑executable work and validate that outputs meet business and technical requirements.
• Run agents in parallel where useful; review, reconcile, and integrate their output.
• Prototype rapidly to gather feedback and inform product direction.

• Design and maintain agent harnesses, including project context, architectural rules, file conventions, allowed dependencies, and review checkpoints.
• Use test‑driven practices to constrain agent output and catch drift early.
• Ensure appropriate automated test coverage across unit, integration, end‑to‑end, and contract tests based on risk.
• Review agent‑produced code for correctness, security, maintainability, and architectural fit.
• Enforce patterns that keep codebases maintainable as AI agents contribute to development.

• Build solutions using design systems, tool use, APIs, function calling, RAG, DAG, MCP, context engineering, harness engineering, and multi‑agent workflows where appropriate.
• Evaluate models and AI tools across providers based on cost, quality, latency, reliability, security, and fit for purpose.
• Implement evals, monitoring, logging, and guardrails so AI systems are measurable and supportable.
• Design for reliable and repeatable outputs where the business requires consistency.
• Communicate technical concepts, tradeoffs, risks, and recommendations clearly to technical and non‑technical stakeholders.
• Partner with architecture, security, and AI governance to align solutions with enterprise standards.

• Strong understanding of Product Management, UI/UX concepts, Business Analysis, Analytics, and SDLCs.
• 5+ years of professional software engineering experience, including senior‑level code review and architectural judgment.
• Demonstrated experience using AI coding agents or AI‑assisted development tools to ship production software beyond basic autocomplete or experimentation.
• Ability to decompose business problems into clear technical specifications, implementation plans, tests, and review checkpoints.
• Strong test‑driven development and automated testing practices, including using tests to validate AI‑generated or agent‑produced code.
• Practical experience building or operating LLM‑based systems in production, including evaluation, monitoring, and handling non‑deterministic behavior.
• Experience working in enterprise environments with security, governance, data‑handling, and production support constraints.
• Strong written and verbal communication skills, including the ability to explain technical tradeoffs to technical and non‑technical stakeholders.
• Bachelor’s degree in Computer Science, Engineering, a related field, or equivalent practical experience.

• Direct experience building in React, React Native, and AWS.
• Experience with Product Management, UI/UX, Business Analysis, Analytics, and SDLCs.
• Experience with AWS services relevant to AI…