About Us

We're a fast-growing AI startup based in Austin, Texas, dedicated to building tools that give companies real visibility into whether their AI agents are actually working.

Our platform provides operational health monitoring and quality evaluation for AI agents — giving founders and teams real-time insight into every run, every trace, and every output. We're building for both technical teams and non-technical founders who need clear, actionable signal without the engineering overhead.

Our stack includes Python microservices, real-time trace ingestion via OpenTelemetry, LLM orchestration across multiple providers, a credit-based evaluation engine, and integrations across the AI ecosystem — LangChain, AWS Bedrock, and custom-built agents.

We're early. The engineers who join now will shape the product, the architecture, and the direction of the company.

The Opportunity

We're looking for a curious, driven Python engineer who wants to build real AI infrastructure — not just maintain it.

This role is ideal for someone who:

• Is bright, quick to learn, and picks up new technologies quickly
• Is diligent and always thinking about solutions, not just problems
• Builds projects outside of school or work because they genuinely enjoy it
• Wants to help create a product from the ground up

You don't need to know everything yet. What matters most is how quickly you learn and how excited you are to build. You'll work closely with product and engineering to design and build the systems that power our platform.

What You'll Work On

This is a backend engineering role. You'll build the Python infrastructure that powers our AI platform — the services, pipelines, and data systems that make agent observability and quality evaluation possible.

You'll contribute directly to the core systems behind our platform:

Agent Data Infrastructure:

• Building and maintaining the agent DB layer — agents, runs, agent_outputs, and quality_results tables
• Writing Python services that ingest, process, and store real-time agent trace data
• Designing data pipelines and backend logic that support live monitoring at scale

Observability & Evaluation Systems:

• Building integrations with OpenTelemetry and agent frameworks like LangChain and AWS Bedrock
• Supporting the credit-based LLM-as-judge evaluation engine — scoring pipelines, datasets, and experiments
• Creating systems that support asynchronous workflows, background jobs, and messaging queues

Platform Engineering:

• Building Python microservices that power our core platform
• Integrating APIs from third-party platforms and AI providers
• Supporting containerization, cloud deployment, and production reliability

You'll be involved across the full lifecycle: problem → design → build → deploy → iterate.

Your code will go into production and be used by real companies.

What We're Looking For

We're much more interested in how you think and build than a checklist of technologies. This role is best suited for someone early in their career — a recent grad, a self-taught builder, or someone with 0–2 years of experience who is still hungry to prove what they can do.

Strong candidates will have the following:

• A degree in Computer Science, Mathematics, or Engineering — or currently pursuing one
• Experience writing Python projects — personal, academic, or professional
• Curiosity about AI, LLMs, agent systems, or data infrastructure
• Personal projects, GitHub repos, or hackathon work you're proud of
• Comfort learning new tools quickly and working with incomplete information
• A desire to solve problems that don't have obvious answers

Helpful experience (not required):

• Python frameworks: Django, Flask, or FastAPI
• ORM libraries and database design
• Working with REST APIs or cloud data systems
• SQL and basic data modeling
• Messaging systems or background job queues
• Containerization or cloud deployment (Docker, AWS, GCP)
• Familiarity with LLMs, OpenTelemetry, or agent frameworks

What Makes This Role Different

This is not a corporate engineering job. We move fast — decisions get made quickly, code ships frequently, and we don't wait for perfect before we ship.

If you thrive in a slow, process-heavy environment, this probably isn't the right fit. But if you want to build and ship real products at a pace that most companies can't match, you'll love it here.

Engineers here:

• Own real parts of the product from day one
• Ship code fast — and see it go into production quickly
• Work directly with the founders
• Help shape architecture decisions
• Solve problems that don't have playbooks

Speed is a feature. We expect everyone on the team to move with urgency, iterate quickly, and not get stuck waiting for all the answers before taking action.

What We Value

• Curious — you enjoy learning new technologies and digging into how things work
• Resourceful — you can figure things out independently without waiting for instructions
• Motivated — you want to build meaningful products that reach real users
• Collaborative — you enjoy solving problems with a tight, focused team
• Persistent — you don't give up when problems get hard

Location

• This is an in-person role in Austin, Texas.
• Working closely together matters at our current stage. The team collaborates from the office during the week.

Employment Type

• Full-time engagement — W2, 1099, or C2C options available.

Job Types: Full-time, Contract

Pay: $80,000.00 - $99,000.00 per year

Application Question(s):

• Do you have any of the following? (List all that apply)

GitHub projects
Hackathon participation
Kaggle competitions
Open-source contributions
Technical blog or tutorials
None yet

• Are you authorized to work in the United States without current or future visa sponsorship?
• Are you able to work from our Austin, Texas office?
• Tell us about a project, experiment, or tool you built using Python or data systems. (Elaborate, don't just provide a link)
• Have you worked with databases or structured data before (SQL, data pipelines, APIs, etc.)? Please elaborate in your own words, not an AI generated summary.

Experience:

• writing Python code: 2 years (Preferred)

Work Location: In person