Software Engineering Intern - Developer Experience and AI Enablement (Winter 2027)

BitGo is the leading infrastructure provider of digital asset solutions, delivering custody, wallets, staking, trading, financing, and settlement services from regulated cold storage. Since our founding in 2013, we have focused on enabling our clients to securely navigate the digital asset space. With a global presence and multiple Trust companies, BitGo serves thousands of institutions, including many of the industry's top brands, exchanges, and platforms, and millions of retail investors worldwide. As the operational backbone of the digital economy, BitGo handles a significant portion of Bitcoin network transactions and is the largest independent digital asset custodian, and staking provider, in the world. For more information, visit www.bitgo.com.

Here's the thesis that drives everything we do: research going back decades consistently shows that roughly 80% of the cost of software lives in operating and maintaining it — not in writing it the first time. Most AI investment in engineering is aimed at the 20%: write code faster, generate boilerplate, autocomplete. We're aiming for the 80%.

That means flaky tests that silently erode confidence in CI. API documentation that drifts from the actual behavior of the endpoints it describes. External dependencies — blockchain node releases, upstream library changes, CVEs — that land at 2am with no one watching. Blips in reliability or emergent incidents that normally wake up on-call engineers. All of it expensive, none of it what engineers want to spend their time on. Our job is to systematically eliminate it.

Solving this well requires a durable execution layer with secure access to every part of our development platform to create a system that runs around the clock, not just when someone has their laptop open. Teams can run Claude Code locally to knock out a bug. That stops when they go home. We're building a development team that doesn't stop.

What we're shipping in the near term:

• Specialized agents — agents optimized for a specific task, capable of working in concert to accomplish goals too ambitious for a single actor today. Evals help us iterate for consistent improvements.
• Continuous work item generation — pipelines that detect drift (test coverage gaps, API doc staleness, SLO regressions, upstream events) and auto-file scoped tasks for internal agents to execute.
• Operational response — an AI-driven incident response layer that monitors observability sources and runbooks to triage and respond to alerts at any hour.

The team's current north star is a 24/7 agentic engineering system: not a copilot, but an autonomous loop that identifies work worth doing, executes it, ships it, validates it — even on nights and weekends, with no humans involved. We're building both the work-generation layer (deciding what to do) and the execution layer (doing it), and closing the loop with verification and measurement. If you want to pioneer how AI systems augment and replace human attention in the engineering process, come build with us.

Responsibilities:

• Create and maintain the agentic platform that AI-powered workflows run on — MCP integrations, agent execution infrastructure, tooling abstractions, observability, and the reliability guarantees that make agents trustworthy enough to deploy on real engineering work.
• Develop the systems that identify engineering work to be done — maintenance debt, NFR drift, flaky tests, API documentation gaps, upstream dependency changes, CVEs — and orchestrate agents that produce effective outcomes without a human in the loop.
• Build and ship agentic workflows that reclaim human time: PR triage, breaking-change pre-screening, incident runbook generation, doc freshness pipelines, and other high-ROI automations identified in partnership with R&D leadership.
• Own CI/CD, build system performance, developer environment tooling, and release infrastructure — the baseline that has to be healthy for agentic workflows to be trustworthy.
• Instrument and operate the measurement framework that proves this work is moving the needle: AI adoption dashboards, cycle time, PR throughput, developer-reported time savings, and quarterly R&D productivity reports.
• Drive AI tooling evaluation and adoption across the engineering org — researching what's coming in the tooling landscape, running early pilots, and bringing back concrete, validated recommendations.
• Partner with engineering teams as the team's primary interface: understand where human time is being lost, identify automation opportunities proactively, and bring a point of view to the roadmap conversation.

Required:

• Driven to rebuild the developer experience in an agentic world.
• Strong programming foundations, with experience building production backend systems.
• Ability to drive projects end-to-end: requirements, design, implementation, instrumentation, and rollout. Includes strong verbal communication skills – engineering is a team sport.
• Excellent written communication — you can write a design doc that makes the tradeoffs legible, and a PR description that reviewers actually read.
• Comfort operating in an environment that moves fast and has real production consequences.

Preferred:

• Experience building AI-powered systems — agent orchestration, LLM-backed workflows, tool use, eval harnesses, or similar. Practical experience with what makes these systems reliable (or not).
• Experience with API design and integration patterns; comfort working with external APIs, webhooks, and event-driven systems.
• Familiarity with MCP (Model Context Protocol) or similar agent integration frameworks.
• Experience with CI/CD systems, GitHub Actions, build tooling, or developer productivity infrastructure.
• Familiarity with observability and measurement — you've built dashboards, tracked metrics, and used data to make an argument for or against a technical direction.
• Exposure to code analysis tooling (AST parsing, static analysis, linting infrastructure) or documentation automation.

If you will be working from Canada: the current target rate for 2027 interns in Canada is $60 CAD per hour. If the market indicates this needs to change, we would share this with you during your interview process.

*Please note that we are required by law to pay you in the currency of the country you will be working from.*