You will build and operate production-grade agentic systems that serve as conversational companions for diehard sports fans. Moving beyond demos, you'll own the orchestration layer, tool design, and evaluation harnesses. This is an opportunity to solve long-horizon reasoning challenges using a cutting-edge stack including Google ADK, MCP servers, and Logfire.
Back to all jobs
Learn about Jack
Agentic Engineer at Snapp Stats
Join an a16z-backed startup led by the co-founder of Caviar to build the ultimate AI companion for sports fans. We are looking for an Agentic Engineer who has moved beyond demos to ship production-grade agents that survive real-world contact. You'll own the orchestration layer, tool design, and eval harnesses for agents that provide real-time insights to bettors and fantasy players. If you have 5+ years of experience and strong opinions on why most agents fail in production, this is your chance to lead the frontier of agentic systems in one of the most emotionally charged markets in tech.
About this role
Role overview
About the company
Snapp is building AI for the Sports Fan— the ultimate conversational companion for diehard fans to sports bettors.
We use AI agentic systems and LLMs with access to comprehensive sports databases, real-time APIs, and AI-powered content tools to truly engage the passionate fan. Our early adopters are sports bettors and fantasy players looking for detailed insights and personalized recommendations — delivered in an intuitive, easy-to-use experience.
We're venture-backed (a16z speedrun) and led by repeat founders, including the co-founder of Caviar (DoorDash acquisition).
What you'll do
What you will do
- Design and ship agent loops using Google ADK that handle long-horizon tasks across tool calls and partial failures.
- Treat tool design as a first-class engineering discipline by building MCP servers that expose sports data and user context to agents.
- Establish rigorous evaluation and observability standards using trajectory evals, ground-truth datasets, and production tracing via Logfire.
Who you are
Who this is a fit for
- Has 5+ years of software engineering experience with at least 1.5 years shipping production-grade agentic systems or LLM products.
- Demonstrates deep discipline in evals and observability, reaching for traces and regression harnesses rather than "vibes-based" prompt tweaking.
- Possesses strong SWE fundamentals in Python and distributed systems with a workflow optimized for coding-agent tools like Cursor or Claude Code.
Why this role
Why this role is remarkable
- Work at the intersection of AI and sports with a team backed by a16z and led by a repeat founder with a major exit to DoorDash.
- Ship agents that handle real-world complexity, moving from simple chat interfaces to proactive systems that compound user context and provide personalized insights.
- High-autonomy environment where your architectural decisions and tool designs reach real users within the same week.
Jack & Jill
How Jack & Jill work together
I get to know what you’re great at, then find roles you’d never find yourself.Ok, I'll go first. I'm Jack, an AI that gets to know you on a quick call, learning what you're great at and what you want from your career. Then I help you land your dream job by finding unmissable opportunities as they come up, supporting you with applications, interview prep, and moral support.
I recruit from Jack’s network and make the intro when I spot a great match.And I'm Jill, an AI Recruiter who talks to companies to understand who they're looking to hire. Then I recruit from Jack's network, making an introduction when I spot an excellent candidate.
Meet Jack
Jack gets to know what you're great at and what you want next, then searches 15 million jobs daily and helps you discover roles at companies like this.
How does this work?
Jack’s an AI agent for job searching and career coaching. He works for you.
Jill is the AI recruiter working for the company. She recruits from Jack’s network.
If it’s a match and the company wants to meet you, they’ll make the intro. In the meantime, if you’d like, Jack will send you excellent alternatives.