How does swipeandhired work?

You set your target roles, salary floor and locations once. swipeandhired scores matching postings against your profile, drafts tailored application materials with AI, and either lets you swipe to apply, one tap at a time, or runs fully on autopilot. Every application is tracked in your dashboard.

Which ATS platforms does swipeandhired support?

All of them. swipeandhired applies on every applicant tracking system (ATS) employers use, including Workday, SmartRecruiters, Greenhouse, iCIMS, Lever, Ashby, Taleo, SuccessFactors, Oracle Cloud and Jobvite, and on a company's own careers page when it uses none of them. You can also bring any posting yourself by link or pasted text.

Can I cancel my subscription?

Anytime, in one click from the billing portal in Settings. Your plan stays active until the end of the current billing period. No retention calls, no dark patterns.

Is my data used for training AI models?

No. Your resume and application data are processed only to run the service for you, matching, drafting, and submitting applications. We never sell your data. If you bring your own AI provider key, requests go directly to your provider under their terms.

Working Student (f/m/d) LLM Wiki & Agentic AI Knowledge Systems at NXP Semiconductors, Hamburg

Working Student (f/m/d) LLM Wiki & Agentic AI Knowledge Systems at NXP Semiconductors in Hamburg. Part-time. EUR 19.4 an hour. Apply with swipeandhired.

Join us as a working student to help build and scale an LLM Wiki as a collaborative AI-native knowledge and working environment .
Our team manages complex subsidy programs combining regulatory requirements, business processes, technical documentation, structured data, and collaboration across many stakeholders. We want to fundamentally improve how this knowledge is created, connected, maintained, and used with AI.
We are looking for someone with hands-on experience using or building an LLM Wiki, AI-native knowledge base, RAG environment, agentic workspace, or comparable solution , whether through personal projects, university work, open-source projects, or professional experience.
Together, we will develop our LLM Wiki concept into a collaborative environment suitable for corporate production use. It will combine human-governed, AI-curated knowledge with controlled workspaces in which users and AI agents jointly develop knowledge, content, processes, and solutions. We are looking for someone who enjoys building, experimenting, and learning , not only discussing AI concepts.

Key Responsibilities

Build, configure, and continuously improve our LLM Wiki and associated AI-native knowledge environment.
Design structures for AI-readable knowledge, including metadata, context, references, relationships, templates, and workspaces.
Experiment with context engineering, retrieval, knowledge curation, and AI-assisted content creation .
Develop and test AI agents that can search, connect, challenge, update, and help create knowledge.
Explore different LLMs, agent approaches, and tools and evaluate their suitability for different tasks.
Develop controlled workflows for turning collaborative and AI-generated content into reviewed, authoritative knowledge.
Test source traceability, permissions, context boundaries, conflicting or outdated information, hallucinations, and other failure modes.
Work directly with pioneer users, gather feedback, and translate findings into practical improvements.
Prototype new approaches and help develop reusable templates, workflows, onboarding, administration, and governance practices.
Document architecture decisions, experiments, implementation choices, and test results.

Job Qualifications

Currently enrolled in a Bachelor’s or Master’s degree program. Computer science, IT, data science, information systems, business informatics, or related fields are welcome, but practical experience matters more to us than your specific field of study .
Hands-on experience with an LLM Wiki, AI-native knowledge system, RAG environment, agentic workspace, or comparable solution. Personal projects and self-directed experimentation explicitly count.
Ability to explain something you have actually built, configured, or used intensively, including what worked, what did not, and what you learned.
Practical experience with modern LLMs and AI tools, including areas such as prompting, context management, retrieval, agents, or tool use.
Basic programming or scripting skills and the ability to turn ideas into working prototypes.
Interest in how knowledge should be structured so that both humans and AI systems can use it effectively .
A structured and experimental mindset with attention to source traceability, permissions, data quality, versioning, maintainability, and safe AI use.
Ability to work independently and collaborate closely with domain experts and users.
Fluent business English.
Experience with technologies such as Microsoft 365, Copilot, Claude, SharePoint, Microsoft Graph, Confluence, Jira, APIs, Python, Git, knowledge graphs, vector databases, or retrieval systems is beneficial, but we do not expect you to know all of them .

We particularly encourage applicants who have built their own LLM Wiki, AI knowledge base, personal AI workspace, RAG system, agent environment, or similar project to apply. Please tell us briefly what you built and, where possible, share a link, screenshot, repository, or description of your setup.

What NXP Offers

An attractive hourly wage of €19.40
30 vacation days per year
Flexible working hours
Access to an on-site canteen
Networking initiatives and Employee Resource Groups such as Young Community, No Extra Planet, NXP Equal, Women in NXP, and more — fostering both professional and personal exchange

Please note: The successful candidate may/will be responsible for security related tasks. The assignment may/will be in scope of security certifications, therefore a conscious and reliable way of working is necessary.

More information about NXP in Germany...

#LI-4da9