Internship / Master Thesis: Quality Gate for AI-Assisted Delivery

Start date: February 2027 · Duration: 6 months
Please include your latest academic transcripts with your application. Applications submitted without transcripts will not be considered.

Agentic development is becoming the default way we build software at ELCA. Agents write a growing share of the code, and architects now review far more than they write. The bottleneck has moved: the hard part is showing that the output is safe to ship, and who approved it. Our clients (Swiss banks, insurers, public administrations and critical infrastructure operators) are starting to ask which parts of a system an AI wrote, with which model, and who signed them off.

In this 6-month master thesis or internship starting in February 2027, you will build a quality gate for AI-assisted delivery: it classifies the risk of a piece of work, records where the AI's output came from, names the moments a human must sign, and checks acceptance criteria per artefact type, mechanically wherever possible. We want something engineers run, not a policy document: fast, able to block a pull request, and producing a record a client can read.

Your tasks

• Survey the state of the art (in-toto, SLSA, Sigstore, SPDX, CycloneDX, OPA/Rego, EU AI Act documentation) and build on established standards
• Define a risk classification (assist, supervised, autonomous × regulated, production-facing) and the controls each class triggers
• Specify a provenance model capturing what was AI-generated, with which tool and model, and who accepted it, automatically from commits, pull-request metadata and agent logs
• Define human sign-off points and machine-checkable acceptance criteria per artefact type (code, tests, ADRs, infrastructure-as-code, documentation), expressed as a versioned YAML schema
• Make the gate executable: CLI first, CI job second, with an agent self-check and a blocking pull-request check running in under three minutes
• Write a signed gate record at each release, handle exceptions as reviewed pull requests with an expiry date, and evaluate the gate on a real ELCA codebase (false positives, runtime, developer friction)

What we offer

• A dynamic, collaborative and multicultural environment across international sites
• Access to our agentic engineering platform, including frontier-class open-weight models on ELCA infrastructure
• Work that ships: the gate is planned to become part of ELCA's 2027 delivery standard
• Internal coding events such as Hackathons and Brownbag sessions, and monthly After-Works

About your profile

• Master's student in Computer Science or Software Engineering at EPFL or ETH Zürich
• Strong programming skills in Python, TypeScript, Go or Java; fluent with Git and CI/CD (GitHub Actions, GitLab CI, Azure Pipelines)
• Interest in supply-chain security, static analysis, policy-as-code or developer tooling
• Hands-on experience with agentic coding tools (Claude Code, Copilot, Cursor) and opinions on where they break
• Ability to turn a standard or regulation into a specification an engineer can implement
• English is our working language; French or German is a plus