Software Engineering Intern

About TraceRoot.AI

Open source self-improving layer for AI agents

Tech

TraceRoot is building the open-source self-improving layer for AI agents — observability that detects failures in production, root-causes them against your source code and GitHub history, opens verified fix PRs, and evals every fix — so your agent gets better with every release. Our stack: - Python (FastAPI, Celery) and TypeScript (Next.js 15, React 19) across our platform and agent layers - ClickHouse for time-series trace storage; PostgreSQL for relational metadata; Redis for queuing - OpenTelemetry-compatible Python SDK with native support for OpenAI, Anthropic, Gemini, and 10+ other LLM providers - Agentic root cause analysis engine with GitHub integration for bug tracking and code version history - AWS (EKS Fargate) + Helm/Terraform for deployment; fully self-hostable via Docker Compose

The role

As the **engineering intern** at TraceRoot, you’ll work side-by-side with the founders to build the product and shape our engineering culture from the ground up.\You’ll wear many hats, touching everything from AI systems and user-facing features to backend infrastructure and open-source SDKs.We move fast, debate hard, and execute even harder, shipping new features weekly and iterating live with users. You’ll work in person with the founders at least 3 days a week, white boarding, coding, and shipping together. If you love building fast, solving hard problems head-on, and seeing your code impact real users within days, you’ll fit right in.## What You’ll Do* **Talk to users often** to deeply understand how to improve TraceRoot’s AI and UX (you can expect to spend 10-20% of your time on support)* **Ship full-stack features** and build the foundational building blocks that users will use to build their apps seamlessly* **Maintain our open-source projects** to help grow and engage our developer community* **Improve our AI agents’ performance, reliability, and edge-case handling** to continuously enhance AI output quality (for both function + design)* **Build robust infrastructure** for our end-to-end platform to power millions of telemetry events## Requirements* **Strong full-stack experience with React, TypeScript, and Node.js:** you’ve shipped production features end-to-end* **Strong sense of ownership:** you’re autonomous and own features from start to finish* **Strong communicator:** you write clearly, think rigorously, and can collaborate well within small teams* **Scrappy and execution-driven:** you move fast, make pragmatic decisions, and care about results over process, bias for action is in your DNA.* **Relentless builder mindset:** you thrive under pressure, love solving hard problems, and make things happen with limited resources## Preferred Experience* **Multi-agent systems:** you’ve designed or shipped multi-agent systems, AI-powered coding tools, LLM orchestration frameworks, or automated code workflows* **Observability tooling:** you’ve built or contributed to systems like tracing pipelines, logging, search infra, metrics platforms, or other developer-facing observability tools* **Startup experience:** you’ve worked at early-stage startups or have been a founder yourself

Skills

• Node.js
• Python
• React
• TypeScript