Research Analyst Intern

Constructor

OUR MISSION Constructor’s mission is to enable all educational organisations to provide high-quality digital education to 10x people with 10x efficiency.  With strong expertise in machine intelligence and data science, Constructor’s all-in-one platform for education and research addresses today’s pressing educational challenges: access inequality, tech clutter, and low engagement of students. PLEASE SEND YOUR RESUME IN ENGLISH ONLY. Interns are NOT eligible for equipment and other benefits as the position is temporary. The Reality The frontier models are converging into commodities; the engine is no longer the differentiator. The scarcity in 2026 is not the model. We are not looking for people to fine-tune Llama on toy datasets or write "better prompts." We are building the runtime systems that turn probabilistic token generation into reliable workers that finish 50-step tasks without spiraling. We are solving the math of multi-step reliability through engineering, not wishful thinking. What You Will Solve You will work on the Agentic Harness, treating the LLM as a component within a larger, deterministic control system. Your research will focus on: * Architecting loops that survive error accumulation. You will build verification layers that force the agent to recognize its own hallucinations and self-correct. * You will implement systems where the agent compiles its own constraints and the harness enforces them via constrained decoding or external execution. * You will optimise KV-cache hit rates and design "restorable compression" strategies to prevent attention decay. Who We Are Looking For We are looking for systems thinkers who happen to know ML, not the other way around. * You know that a demo is not a product. You are interested in the "boring" engineering: state machines, retries, idempotency, serialisation — that actually makes agents work. * You are comfortable working with the raw output of the model and building robust software in Python or Rust around it. * You understand why dynamic tool loading destroys inference economics. You prefer deterministic guardrails over "prompting it to be nicer." * You are willing to read a 500-line trace of a failed agent loop to find the exact moment the context drifted. You care about the "last mile" of reliability. WHAT WE OFFER FOR INTERNS: * Internship Duration: from 2 months or more  * Type of internship: * 100% remote * or hybrid in the office in Bremen (GER), Sofia (BG), Belgrade (SRB), Istanbul (TR), Sakarya (TR), Singapore (SGD)  WHAT WE OFFER * 💻 Choice of work equipment (e.g., laptop, monitor, etc.) * 🇬🇧 English classes (iTalki – $130 monthly) * ⏰ Flexible schedule (we usually work between 09:00/10:00 and 18:00/19:00 CET or EET) * 👶 Newborn bonus (€500 per child) * 🧠 Patent remuneration * 🌴 Paid leave * 🧑‍💻 Remote work in locations without our offices * Hybrid work in locations with offices (2 days in-office, 3 days remote) Constructor fosters equal opportunity for people of all backgrounds and identities. We are led by a gender-balanced board committed to building a diverse and inclusive organisation where everyone can become their best self. We do not discriminate based on age, disability, gender identity, sexual orientation, ethnicity, race, religion or belief, parental and family status, or other protected characteristics. We welcome applications from women, men and non-binary candidates of all ethnicities and socio-economic backgrounds. We encourage people belonging to underrepresented groups to apply.

Constructor Knowledge Labs

Constructor Knowledge Labs (CKL), Bremen, Germany In collaboration with Constructor University and Constructor Technology Duration: Flexible ABOUT THE POSITION Constructor Knowledge Labs (CKL) invites applications for a research internship embedded in the research direction “AI for Semantic Structures, Reasoning Flows & Personalized Content Generation.” The internship is situated within an active research program jointly developed with Constructor University and Constructor Technology, focusing on methods for semantic structure extraction, reasoning-flow modeling, and adaptive content generation in scientific and educational domains. The internship supports ongoing foundational research on the analysis and representation of deep semantic and pedagogical structures in unstructured and semi-structured data. Core themes include semantic parsing, structured NLP, graph-based representations, and learner-aware content modeling. The intern will contribute at an internship level to selected research tasks under close supervision, gaining hands-on experience with research workflows, experimental setups, and prototype systems. The position provides exposure to interdisciplinary research at the intersection of artificial intelligence, natural language processing, knowledge representation, and learning sciences, with clearly scoped responsibilities appropriate for an internship role. MAIN RESPONSIBILITIES: * Prepare and organize research data, including scientific and educational texts, datasets, and related metadata, for use in semantic and reasoning-oriented analyses. * Support the analysis of unstructured and semi-structured data and its transformation into structured representations such as semantic annotations, concept structures, or reasoning graphs. * Assist in selected research experiments related to semantic structure extraction, reasoning-flow modeling, or adaptive content generation, under supervision. * Support the implementation and evaluation of baseline models, analysis pipelines, or prototype components. * Conduct literature review and contribute to research documentation and internal reports. * Participate in regular research meetings and collaborative discussions within the research team. REQUIREMENTS: * Currently enrolled in a BSc or MSc program in Computer Science, Artificial Intelligence, Data Science, Computational Linguistics, Cognitive Science, or a closely related field. * Solid programming skills, preferably in Python, with basic experience in data processing or machine learning workflows. * Foundational familiarity with concepts in machine learning and/or natural language processing. * Strong analytical thinking and interest in research-oriented work. * Ability to read and summarize scientific literature. * Good written and spoken English. WE OFFER * Research internship with flexible duration in an international, interdisciplinary research environment. * Participation in active research projects at the intersection of AI, knowledge systems, and applied research, with a clearly scoped internship-level contribution. * Close supervision and mentoring by leading PIs and senior researchers, whose work shapes current research agendas and attracts significant scholarly attention and citations. * Opportunity to contribute to academic publications, embedded in established research groups with consistent presence at top-tier conferences and journals. * Flexible working arrangements, including hybrid or remote options. APPLICATION DETAILS Please submit the following documents in English: * CV * Short motivation letter (max. 1 page) explaining your interest and relevant skills * Transcript of records (GPA obligatory) Deadline for full consideration: Applications are reviewed on a rolling basis

Constructor Knowledge Labs

Constructor Knowledge Labs (CKL), Bremen, Germany In collaboration with Constructor University and Constructor Technology Duration: Flexible ABOUT THE POSITION Constructor Knowledge Labs (CKL) invites applicants for a research internship in the area of knowledge discovery and representation, with a focus on transforming unstructured data into interpretable, navigable, and actionable cognitive structures. The internship is embedded in an active research direction jointly developed with Constructor University and Constructor Technology, exploring how modern AI systems (particularly large language models and graph-based methods) can be used to construct shared cognitive maps from heterogeneous knowledge sources such as scientific publications, educational materials, and digital artifacts. The intern will work closely with researchers and engineers on ongoing research activities, contributing to the design, implementation, and evaluation of methods for knowledge representation, semantic structuring, and adaptive reasoning. The position offers hands-on exposure to applied research at the intersection of AI, knowledge graphs, and human-centered knowledge systems. ---------------------------------------------------------------------------------------------------------------------------------- MAIN RESPONSIBILITIES: * Prepare and organize research data, including text collections, research publications, datasets, and related metadata, for use in analytical and modeling tasks. * Work with unstructured and semi-structured data, supporting its analysis and transformation into structured representations such as knowledge graphs, semantic annotations, or concept mappings. * Assist in selected research experiments and analytical tasks related to knowledge discovery, reasoning, or information extraction, under supervision. * Conduct literature review and support research documentation, with potential contribution to internal reports or academic publications. ---------------------------------------------------------------------------------------------------------------------------------- REQUIREMENTS: * Currently enrolled in a BSc or MSc program in Computer Science, Data Science, AI/ML, or a closely related field. * Solid programming skills, preferably in Python. * Basic familiarity with machine learning concepts and data processing workflows. * Strong analytical thinking and interest in research-oriented work. * Good written and spoken English. ---------------------------------------------------------------------------------------------------------------------------------- WE OFFER * Research internship with flexible duration in an international, interdisciplinary research environment. * Participation in active research projects at the intersection of AI, knowledge systems, and applied research, with a clearly scoped internship-level contribution. * Close supervision and mentoring by leading PIs and senior researchers, whose work shapes current research agendas and attracts significant scholarly attention and citations. * Opportunity to contribute to academic publications, embedded in established research groups with consistent presence at top-tier conferences and journals. * Flexible working arrangements, including hybrid or remote options. ---------------------------------------------------------------------------------------------------------------------------------- APPLICATION DETAILS Please submit the following documents in English: * CV * Short motivation letter (max. 1 page) explaining your interest and relevant skills * Transcript of records (GPA obligatory) Deadline for full consideration: Applications are reviewed on a rolling basis