Junior Software Engineer (AI-Forward)

Texas Sports Academy Main•Austin, TX

1d•Onsite

About The Position

As a Junior Software Engineer with Texas Sports Academy, you'll help build the software that runs our school, student records, academic mastery tracking, training data, parent portals, admissions, and the AI-powered tools our guides and coaches use every day. This is an early-career, AI-forward seat. You'll work directly with the founders and senior engineers, ship code every week with AI in your loop, and grow into the LLM-powered features that make our school feel nothing like a traditional school.

Requirements

Bachelor's or master's degree in Computer Science, Engineering, Math, or Physics.
0 to 2 years of full-time engineering experience. Strong internships, side projects, and shipped personal work count.
Daily, fluent use of AI coding tools (Claude Code, Cursor, Codex, Windsurf, Aider, or equivalent) as your default way of writing software.
Comfortable in a modern web stack (TypeScript / React / Node or Python / Postgres / AWS or GCP).
Excellent written English.
Based in Austin, TX.

Nice To Haves

At least one shipped LLM-powered project, school project, hackathon, or side project, with some kind of eval story.
Agent frameworks (LangGraph, CrewAI, Mastra, custom), vector search / RAG, evals (Braintrust, LangSmith, custom), prompt caching, MCP servers, structured output / tool-use, or voice agents.
Public GitHub or a personal AI project we can actually try.
A personal project you built because you wanted to.
Background in education, edtech, or sports.

Responsibilities

Building and shipping product features across the full stack every week, with AI coding tools running alongside you.
Contributing to real LLM-powered product features: tutoring agents, parent-facing copilots, coach-facing dashboards, retrieval over student data, and the evals behind them.
Working directly with the founders and senior engineers on scope and trade-offs, no PM layer in between.
Picking up ownership of smaller systems end-to-end and growing into bigger ones.
Running your own AI coding workflow, prompts, subagents, custom tools, MCP servers, and getting sharper at it every week.
Writing evals and regression tests for AI features the same way you'd write unit tests for classical code.
Ship production code and AI features that real students, parents, and staff rely on every day.
Own smaller systems and features end-to-end as you ramp up.
Move fast. Features go from idea to production in days, not quarters, without breaking things.
Level up your AI-engineering chops alongside a senior team.