INTERNSHIP DETAILS

ML Research Intern in Agentic Runtime Systems

CompanyConstructor TECH
LocationBremen
Work ModeOn Site
PostedApril 1, 2026
Internship Information
Core Responsibilities
You will work on the Agentic Harness, focusing on architecting loops that survive error accumulation and building verification layers for self-correction. Your role involves implementing systems for constraint compilation and optimizing KV-cache hit rates.
Internship Type
full time
Company Size
565
Visa Sponsorship
No
Language
English
Working Hours
40 hours
Apply Now →

You'll be redirected to
the company's application page

About The Company
Constructor Tech is an all-in-one software platform that covers 21+ scenarios to support the complete lifecycle of education and research, based on generative AI, MetaPresence, and neuroscience advances. It is built to cater to the needs of schools, higher education institutions, and corporate training, offering solutions for teaching, learning, research, and administration. As a part of Constructor Group, Constructor Tech has access to cutting-edge research and technologies, as well as a broad scientific, business and talent network. This helps Constructor Tech build a unique platform with a modern, open architecture and user experience, with comprehensive scenario and global coverage, to help each student, teacher, and researcher be more efficient and effective. Constructor Tech has 2,000+ partners and customers and 2.5M+ users. With a team of 300+ employees (over 50% in R&D) across 28 locations, headquartered in Switzerland and with offices in seven key locations around the globe, Constructor Tech is solving the challenges of tomorrow.
About the Role

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.

Key Skills
Machine LearningSystems ThinkingSoftware DevelopmentPythonRustError AccumulationSelf-CorrectionDeterministic ControlState MachinesRetriesIdempotencySerializationKV-Cache OptimizationAttention DecayRobust SoftwareDynamic Tool LoadingReliability
Categories
TechnologyEducationScience & ResearchData & AnalyticsSoftware
Benefits
Choice Of Work EquipmentEnglish ClassesFlexible ScheduleNewborn BonusPatent RemunerationPaid Leave