AI Chat Assistant & Knowledge Engineering Intern – LLM‑Powered Security Analytics, Documentation & Retrieval‑Augmented Generation (RAG) Experience at careerzynith
Why careerzynith?
careerzynith is a fast‑growing cybersecurity scale‑up rooted in Swiss precision and innovation. Born from cutting‑edge research at ETH Zurich, we deliver AI‑driven security analytics that protect IT, OT, and IoT environments across Europe and beyond. Our flagship platform, careerzynith.NDR, empowers enterprises to monitor, detect, and respond to threats with unprecedented speed, accuracy, and automation.
At careerzynith we blend world‑class engineering with a remote‑first, collaborative culture. We champion autonomy, trust, and continuous learning, giving ambitious talent the freedom to shape their own impact while working alongside seasoned security experts, data scientists, and product innovators.
Position Overview
We are seeking a motivated AI Chat Assistant & Knowledge Engineering Intern to join our dynamic team for a six‑month, full‑time internship (remote in Switzerland/Germany or from our Zurich office). In this role you will design, build, evaluate, and continuously improve an internal AI assistant that powers engineers, security analysts, and business stakeholders. Simultaneously, you will lead the transformation of our technical documentation into structured, machine‑readable knowledge assets that enable high‑quality, context‑aware responses.
Key Responsibilities
AI Chat Assistant Development (≈ 50 % of effort)
- Extend and refine careerzynith’s internal large‑language‑model (LLM) powered assistant, initially for internal use with the potential for future externalization.
- Build and iterate on a Retrieval‑Augmented Generation (RAG) pipeline: document ingestion, chunking, embedding generation, vector search, ranking, and answer synthesis.
- Design and execute offline and human‑in‑the‑loop evaluation experiments, measuring precision/recall of retrieval, response helpfulness, hallucination rates, latency, and cost metrics.
- Collaborate with security engineers and data scientists to integrate domain‑specific knowledge, ensuring the assistant can reason about complex security concepts.
- Document the architecture, data flows, and evaluation results to create reusable internal knowledge for future AI projects.
Knowledgebase & Documentation Engineering (≈ 50 % of effort)
- Audit existing technical assets (specifications, API docs, runbooks, playbooks, product guides, research notes) and identify gaps that affect LLM accuracy.
- Add missing technical content, rewrite ambiguous sections, and refactor material into LLM‑friendly structures such as FAQ patterns, Q&A primitives, and step‑by‑step procedures.
- Develop lightweight authoring standards and contribution guidelines so ongoing documentation remains “assistant‑ready” and user‑friendly.
- Work closely with the Technical Writing team to ensure consistency, proper labeling, and version control across all knowledge assets.
- Implement automated pipelines that continuously ingest updated documentation into the vector store, keeping the AI assistant current.
What You’ll Gain
- Hands‑on experience with state‑of‑the‑art LLM frameworks (e.g., LangChain, Haystack, Semantic Kernel) and vector databases.
- Mentorship from senior AI engineers and security experts who will guide your technical growth.
- Exposure to real‑world cybersecurity challenges, bridging the gap between AI research and production‑grade security operations.
- Opportunities to present your work to senior leadership, influencing product roadmap and AI strategy.
- Flexible remote work arrangements, with the option to collaborate from our Zurich office for face‑to‑face brainstorming sessions.
Essential Qualifications
- Currently pursuing or holding a Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Data Science, or a closely related field.
- Strong enthusiasm for AI, machine learning, and natural language processing, with a willingness to dive deep into emerging technologies.
- Proficiency in Python and hands‑on experience with at least one AI/LLM application framework (e.g., LangChain, Haystack, Semantic Kernel) or a demonstrated ability to learn such frameworks quickly.
- Excellent written communication in English; ability to produce clear, concise, audience‑aware documentation.
- Demonstrated skill in reorganizing messy information into structured, navigable, well‑labeled content.
- Basic understanding of embeddings, vector databases, and information retrieval concepts.
- Comfortable using Git/GitHub/GitLab for collaborative development and version control.
- Strong analytical and problem‑solving abilities, with a proactive, self‑motivated attitude suited to a fast‑paced start‑up environment.
Preferred Qualifications
- Prior exposure to cybersecurity domains (network security, OT/IoT protection, threat detection) or a strong personal interest in the field.
- Experience with evaluation methodologies for LLMs, including human‑in‑the‑loop testing, A/B testing, or metric‑driven analysis.
- Familiarity with cloud platforms (AWS, GCP, Azure) and containerization technologies (Docker, Kubernetes) for scalable AI deployments.
- Knowledge of documentation tools such as MkDocs, Sphinx, or Confluence, and experience building automated documentation pipelines.
- Ability to work across multiple time zones and cultures, collaborating effectively with teams spread throughout Europe.
Core Skills & Competencies
- Technical Acumen: Python programming, LLM integration, vector search, and data preprocessing.
- Communication: Clear writing, ability to translate technical concepts for diverse audiences, and strong presentation skills.
- Collaboration: Team player who thrives in cross‑functional environments, comfortable engaging with security engineers, product managers, and technical writers.
- Curiosity & Learning Agility: Eagerness to stay current with AI research, cybersecurity trends, and best practices in knowledge management.
- Organizational Skills: Ability to manage multiple work streams, prioritize tasks, and meet deadlines in a dynamic setting.
Career Growth & Development
careerzynith invests heavily in the professional development of its interns. You will have access to:
- Regular technical workshops on LLM engineering, RAG architectures, and cybersecurity fundamentals.
- Mentorship programs pairing you with senior AI researchers and security architects.
- Opportunities to attend industry conferences (virtual or in‑person) and present your project outcomes.
- Potential pathways to full‑time roles after the internship, based on performance and business needs.
Work Environment & Culture
Our culture is built on openness, diversity, and a shared passion for solving complex problems. At careerzynith you will experience:
- A remote‑first mindset that trusts you to deliver results from wherever you are most productive.
- Regular virtual coffee chats, team‑building activities, and an inclusive environment where every voice is heard.
- Transparent communication from leadership, with clear visibility into company goals, product roadmaps, and financial health.
- A commitment to work‑life balance, offering flexible hours, generous vacation policies, and mental‑health resources.
Compensation, Perks & Benefits
While exact figures will be discussed during the interview process, you can expect a competitive internship stipend, along with a suite of benefits designed to support your growth and wellbeing:
- Flexible remote work arrangement (with optional access to our Zurich office).
- Professional development budget for courses, certifications, or conference attendance.
- Access to cutting‑edge AI tools, cloud resources, and internal datasets for experimentation.
- Health and wellness allowances, including mental‑health support.
- Team outings, virtual hackathons, and social events that foster community.
How to Apply
If you are an enthusiastic AI‑curious student who thrives in a high‑energy, innovative environment, we want to hear from you. Submit your resume, a brief cover letter outlining your interest in AI‑driven cybersecurity, and any relevant project work (e.g., GitHub repos, notebooks, or documentation samples).
Join careerzynith and help shape the next generation of AI‑powered security assistants while sharpening your expertise in knowledge engineering. Your ideas will directly influence how enterprises defend their most critical assets.