Time since we first saw it
Day 213
Up longer than most. Similar jobs usually come down between day 4 and day 77.
From 51 similar postings that came down. Coming down is not always a hire.
ML Research Intern in Agentic Runtime Systems
Bremen, Germany
Open 7 months, first seen by us 213 days ago- Pay
- Pay not listed
- Work setting
- Not stated
- Employment
Employment terms need review — employment source
Please send your resume in English only. Interns are NOT eligible for equipment and other benefits as the position is temporary. The Reality
Read the full posting
Before you apply
- New graduates
- For current students
Job title: ML Research Intern in Agentic Runtime Systems
What you’ll work on
Full postingBuild verification layers that make agents detect and self-correct hallucinations
Enforce agent constraints via constrained decoding or external execution
Optimise KV-cache hit rates and design restorable compression strategies
Architect agent loops that survive error accumulation
From the employer’s posting
You will build verification layers that force the agent to recognize its own hallucinations and self-correct.
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.
Architecting loops that survive error accumulation.
What you’ll bring
All qualificationsCore experience
- Comfortable working with raw model output and building robust software in Python or Rust
- Systems thinking: state machines, retries, idempotency, serialisation
- Willingness to dig through long traces of failed agent loops
Qualification wording
You are comfortable working with the raw output of the model and building robust software in Python or Rust around it.
You are interested in the "boring" engineering: state machines, retries, idempotency, serialisation
You are willing to read a 500-line trace of a failed agent loop to find the exact moment the context drifted.
Benefits in the posting
Full benefits wording- 👶 Newborn bonus (€500 per child)
- 🌴 Paid leave
- 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.
From the employer’s posting.
About Constructor TECH
Constructor’s mission is to enable all educational organisations to provide high-quality digital education to 10x people with 10x efficiency.
In the employer’s words · Read in context
Posting record
Report an errorOpen 7 monthsWe first saw this posting 213 days ago and it is still up. Roles open this long are often slow to fill or kept open to collect applications.
- Status in our records
- Live
- First seen by us
- Apr 14, 2026213 days ago
- Recorded sightings
- 161
- Last seen by us
- Nov 13, 2026
These dates show when we found the posting. Check the employer’s website to confirm it is still accepting applications.
How this job compares
Constructor TECH is hiring
3 open jobs
- No new data jobs since June
See how this role fits your experience
Add your resume and we’ll mark which of these tools you already use, and point out anything in the posting that could rule you out.
- Python
- Rust
Where the posting names them
- 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."
Your next step
Complete your application on job-boards.eu.greenhouse.io. The employer’s form will show what is required.
Applying through Greenhouse
- No account needed: the form is one page, with an “Autofill my application” option that reads your resume.
- Greenhouse doesn’t read resumes over 2.5 MB, or details placed in a header, footer, text box, table or second column. The file still attaches, but a recruiter has to type you in by hand.
Already applied? Track this application
Demand for AI Engineer roles
New AI Engineer postings at the employers we follow are up 134% over the last 6 weeks compared with the 6 before.
Each bar is one week of new postings. The darkest bars are the last 6 weeks.
Counted from the hiring pages we’ve followed for at least five weeks, so employers we add don’t look like growth. Updated weekly.
About the role
We file this job under AI Engineer, by the work the posting describes.
AI engineers build products on top of AI models that already exist, most often large language models: they connect a model to a company's data and tools and ship the assistants, agents and search features people use.
Postings ask for strong Python or TypeScript, experience with model APIs, retrieval and agent frameworks, and ways to test whether the model's answers are good enough.
An ML engineer trains and serves models; an AI engineer usually starts from a model someone else trained and builds the product around it, though titles often mix the two.
Job description
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)
- 👶 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.
Source details
Source notes
Source excerptsSelected passages from the saved posting. Check the full description for conditions and exceptions.
- Pay
No pay amount identified in the saved description.
- Location & working pattern
Bremen, Germany
- 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
More source context
- 🌴 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.
- Work authorization
No clear work-authorization passage found. Eligibility is unconfirmed.