Thesis - Human-in-the-Loop Calibrated Agent Harness
Technology, Data & Digital · Data, AI & Analytics · Artificial Intelligence · Software Engineering · UI/UX Design
In short
This thesis project explores creating an open, extensible agent harness to improve collaboration between humans and AI agents. It focuses on calibrating human involvement to tasks, moving beyond simple automation or interruption to a shared vocabulary for clarification, confidence, and decision-making.
Responsibilities
- Investigate and prototype an open, extensible agent harness supporting richer human-AI agent collaboration.
- Design clarification mechanisms, such as inline assumption flags and confidence indicators.
- Develop an advisor component to monitor interactions and suggest clarifications.
- Explore how the advisor can support both the AI agent and the human.
- Implement a prototype, potentially using the PI agent harness and an external model provider.
- Evaluate if a richer interaction vocabulary improves alignment, reduces rework, and maintains understanding and control.
Requirements
- Knowledge in Computer Science, Human-Computer Interaction, Software Engineering, Artificial Intelligence, or a related field.
- Experience in at least one programming language and an interest in building and evaluating prototypes.
- Interest in large language models, AI agents, human-in-the-loop systems, or interaction design.
- Eagerness to explore an interdisciplinary research problem spanning software, AI, and human factors.
- Ability to formulate research questions, conduct structured evaluations, and communicate findings clearly.
Desired Qualifications
- Bonus: experience with Python, TypeScript, LLM APIs, agent frameworks, or user studies.
Benefits
- Outstanding opportunity to use skills and imagination to push the boundaries of what's possible.
- Work on challenging projects and build solutions never seen before.
- Be part of a team of diverse innovators.
- Challenged, but not alone.
- Join a team driven to go beyond the status quo to craft what comes next.
Skills
PythonTypeScript
#AI#Agent#Harness#Human-in-the-loop#Calibrated#Thesis#Interaction Design#Software Prototyping#Evaluation#Large Language Models
Our purpose \nTo create connections that make the unimaginable possible.\n\nOur vision\nA world where limitless connectivity improves lives, redefines business and pioneers a sustainable future.\n\nOur values\nPerseverance, professionalism, respect and integrity.\n\nThe future is a place for purpose & vision – ours are clear, and we invite partners, customers and consumers to join us in our journey. \n\nFor a brighter future. For all. Let's #ImaginePossible
Company
EricssonJob Posted
9 hours ago
Employment Type
Internship
Work mode
On Site
Experience Level
Entry
Locations
Karlskrona, Sweden
Qualification
Bachelor
Applicants
Be an early applicant
Similar Jobs
Qualcomm
San Diego, United States of America#AI Solution Engineer
US$99.5–149k/yr Full Time Be an early applicant Posted 4 days ago
Microsoft
United StatesSoftware Engineering Intern – Cloud & Distributed Backend
US$5.69–11.2k/mo Internship Be an early applicant Posted 4 days ago
Microsoft
United StatesSoftware Engineering
Full Time Be an early applicant Posted 4 days ago
Microsoft
United StatesSoftware Engineering Intern – Security & Identity
US$5.69–11.2k/mo Internship Be an early applicant Posted 4 days ago
Microsoft
United StatesSenior Software Engineer
US$120–235k/yr Full Time Be an early applicant Posted 4 days ago
Microsoft
United StatesPrincipal Software Engineer
US$143–275k/yr Full Time Be an early applicant Posted 4 days ago
