Master Thesis in Adaptive Architecture for Human-AI Annotation Systems

Company description:

.

Job description:

Thesis Scope & Problem Statement

This thesis project is intended for two Master's students working together.

The central focus of this Master's thesis is to design, implement, and evaluate a confidence-aware adaptiverification architecture within the existing annotation tool. Instead of applying the same review process every detection or scene, the system will use confidence signals to select an appropriate depth of humverification. This is a software engineering thesis focused on how to structure, integrate, test, and evaluathat adaptive behavior, with particular attention to maintainability, traceability, fallback behavior, andeffective human oversight. Existing AI models provide the application context; developing new perceptimodels is not the primary objective.

Research Objectives & Tasks

The work may include:

Design and integrate a modular architecture with explicit interfaces for confidence providerverification policies, decision logging, and annotator feedbac

Implement confidence-provider components that expose calibrated or normalized signals, such model confidence, model agreement, source model, and object class frequency, through a comminterface.

Implement and compare interchangeable threshold-based and learned decision policies for routingcases to light review, full review, or a second review. Automatic acceptance will be considered onlywhere permitted by safety policy, with low-confidence, out-of-distribution, and safety-critical casrouted to human review.

Integrate attention cues into the annotation interface and record the signals, policy version, selectedreview mode, and human outcome for each routing decision.

Develop automated tests for routing decisions, component interfaces, and fallback behavior.

Benchmark the adaptive architecture against existing manual, sequential, and parallel workflousing annotation correctness, recall on safety-critical classes, error catch rates, task completion time,routing overhead, and human intervention.

Evaluate maintainability and testability through change scenarios, such as adding a confidenprovider or replacing a decision policy.

Conduct a counterbalanced user study to investigate verification behavior, cognitive workload, trucalibration, and susceptibility to automation bias.

Depending on feasibility and measurable added value, the work may also explore out-of-distributiondetection or vision-language-model-derived scene complexity as additional confidence signals. The coevaluation will use fixed policies during controlled experiments; online adaptation is an optional extension.

Who Are We?

You will join the Verification & Validation (V&V) Virtual Driver team at V.A.S., focused on ensuring tintegrity of the software stack for autonomous decision-making and control. The team brings togetherdevelopers with varied backgrounds and seniority, all centered around robust V&V practices. Theenvironment is friendly and helpful, with both in-office development and in-vehicle testing.

Who Are You?

You are a final-year Master's student in Software Engineering, Computer Science, or a related field, withstrong interest in software architecture, software quality, and building maintainable systems. You arecomfortable programming in Python and interested in extending and evaluating an existing softwareplatform in an industrial setting.

You should have a foundation in modular software design, interface design, automated testing, and versioncontrol, together with an interest in empirical software engineering. You should be motivated to comparedesign alternatives and connect architectural decisions with measurable effects on correctnesperformance, maintainability, and testability.

Familiarity with AI-assisted systems, machine learning, computer vision, or human-computer interaction isadvantageous, but prior specialization in machine learning or object detection is not required. An interest inlearning enough about model confidence and human verification to make sound software design decisis important.

Why Join Us?

This thesis offers an opportunity to apply software engineering methods to a concrete industrial challengdesigning an adaptive human-AI workflow that is maintainable, testable, and auditable. You will build on existing annotation platform and prior thesis results, taking the work from architectural design throughimplementation and empirical evaluation.

You will:

Gain hands-on experience in architectural design, component integration, automated testing, andevaluation of an industrial software system.

Investigate how confidence signals can guide human attention while preserving traceability ahuman oversight.

Measure architectural trade-offs across annotation correctness, performance, maintainabilittestability, and human effort.

Collaborate with engineers working on the validation of autonomous transport solutions.

You will gain practical experience in designing and evaluating human-AI systems in a safety-critical context.We look forward to receiving your application letter, academic transcript, and CV in English.

Preferred start date: January 2027Application deadline: 15 November 2026

We value your data privacy and therefore do not accept applications via mail.

Profile description:.

We offer:.