AI Software Lead

First Student is North America's leading provider of student transportation, helping millions of students get to and from school safely each day. Our technology teams build and support the operational, safety, customer, and employee-facing systems behind that work, including our HALO platform. AI is an area of active investment, and this role is part of how we are building practical, reliable, and governed AI-enabled capabilities for the business. About the Role This is not a traditional software engineering role, and "Lead" does not mean managing people. 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. You will not primarily be measured by writing code line-by-line. You will be measured by your ability to direct AI coding agents effectively, create the scaffolding that keeps their work aligned, review their output with senior-level judgment, and ensure the resulting software is reliable, maintainable, and production-ready. When the solution itself is an AI agent - such as a routing assistant, dispatcher copilot, or parent communications agent - you will help design, build, evaluate, and operate it in production. You will work primarily on net-new tools and agents, with some work in existing systems. You will build in our standard stack: React, React Native, and AWS. Many tools may touch student data, so FERPA and enterprise governance are part of the work. You will be a peer in a small AI pod and will help shape the AI governance and delivery practices we are building now. How You'll Work You will operate AI coding agents - such as Claude Code, Codex, Cursor, and successor tools - as a primary means of software production. Your value is not typing speed. It is the judgment to know what to build, how to constrain the agent's work, when the output is wrong, and how to prove the result is right. A key part of the 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. A typical week may include: Translating business problems into specifications, constraints, and implementation plans AI coding agents can execute. Running agents in parallel, reviewing output, and integrating work into maintainable systems. Designing tests, project context, architectural rules, and review checkpoints to keep agent output aligned. Building evals, guardrails, and monitoring for AI-built and AI-embedded systems. Working with stakeholders, architecture, security, and AI governance to clarify requirements and manage risk. Key Responsibilities Lead agent-driven software delivery 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. Maintain quality, reliability, and architectural discipline 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 and operate AI-enabled systems 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. Required Qualifications 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. Preferred Qualifications 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 workloads, such as Bedrock, Lambda, ECS/Fargate, API Gateway, S3, DynamoDB, RDS, or Step Functions. Experience with agent frameworks, RAG, vector databases, embeddings, context engineering, tool use, or function-calling patterns. Experience with LLM observability, evaluation, structured outputs, prompt optimization, guardrails, or deterministic-output patterns. Experience with advanced testing practices such as contract testing, property-based testing, or mutation testing. Experience with Snowflake, Power BI, geospatial, routing, logistics, transportation, or operations-focused software. Experience applying AI within governed enterprise environments, including FERPA-relevant or similarly regulated data. Relevant AWS, AI, cloud, or data certifications. What Success Looks Like At 6 months: You have shipped 2-3 production tools or agents through agent-driven development. You have established agent harness patterns, test-first practices, and review standards that the AI pod can reuse. Stakeholders trust your judgment on where AI can help, where it cannot, and what is required to use it responsibly. At 12 months: You have a portfolio of AI-built and AI-embedded systems running reliably in production. The practices you helped shape are improving delivery speed, quality, and consistency across the team and are beginning to influence broader AI delivery practices across IT. Working Style This role requires initiative, judgment, and clear communication. You should be comfortable clarifying ambiguous objectives, making progress with limited direction, escalating risks early, building trust with stakeholders, and documenting the decisions behind your work. Strong agent-driven engineering requires more discipline, not less. You will be expected to set clear constraints, verify output rigorously, and maintain ownership of the quality of what ships. First for a reason: At First Student, we are a family of 60,000+ employees who take pride in safely transporting more than 5 million students and passengers to and from their destinations each day! Our family of brands include Transco, Total Transportation, Maggies Paratransit, and GVC II. Our employees are at the forefront of safety and innovation; they create and implement the most advanced training and technology the transportation industry has to offer. In the state of Washington, all technician and driving positions, including but not limited to van drivers and any other position requiring employees to drive a company-owned vehicle, are considered safety-sensitive and are therefore subject to drug and alcohol testing, including cannabis. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability or veteran status. First is also committed to providing a drug-free workplace. First will consider for employment qualified applicants with criminal histories consistent with the requirements of the San Francisco Fair Chance Ordinance, Los Angeles Fair Chance Ordinance, and any other fair chance law. Philadelphia’s Fair Criminal Record Screening Standards Ordinance Poster is at this link or upon request .