Back to jobs

Agentic Engineer

Remote Germany, Prague, Hamburg, Berlin, München

Open 4 months, first seen by us 130 days ago
Pay
Pay not listed
Work setting
Working pattern needs review — work setting source
Openness to collaborating with cross-functional teams - from designers to strategists - as well as directly with clients You’re enjoying being part of a team, not a remote desk which prefers to work in isolation most of the time. What You Can Look Forward To
Listed location: Remote Germany,Prague,Hamburg,Berlin,München
Read the full posting
Employment
Permanent — employment source
Employment type in the employer’s posting: Permanent employee
From the employer’s posting

What you’ll work on

Full posting
  • You’ll work closely with the crafts, designers and strategists, and just as easily with the people steering the projects and the business.

From the employer’s posting
We are not a place of rockstars and egos. People here ask questions out loud, show rough work without flinching, and would rather help each other get something right than look clever alone. We push each other, in the good way, and we do not take ourselves too seriously while we are at it. You would be joining that. You’ll work closely with the crafts, designers and strategists, and just as easily with the people steering the projects and the business. There is no wall between you and any of it. Take on the parts you are ready for, and when you want more, a pitch, a client conversation, a bigger call, speak up at the right moment and the door is open. Smaller team. More ownership. Bigger work.
Apply at OH-SO Digital

Posting record

Report an error

Open 4 monthsWe first saw this posting 130 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
Jul 15, 2026130 days ago
Recorded sightings
46
Last seen by us
Nov 22, 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

Time since we first saw it

Day 130

Up longer than most. Similar jobs usually come down between day 1 and day 15.

From 1,368 similar postings that came down. Coming down is not always a hire.

OH-SO Digital is hiring

1 open job

  • No new data jobs since July
Hiring record

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
  • TypeScript
  • AWS
  • Docker
  • Kubernetes
  • Terraform
  • React
Where the posting names them
- Experience building with LLMs or AI systems in production - integration, agents, RAG, or similar - Strong software engineering fundamentals in Python and/or TypeScript, and confidence designing and working with APIs - A habit of treating prompt engineering as a code discipline — with a real understanding of evaluation, guardrails, and reliability
The stack you’ll work with: - Languages & core: Python and/or TypeScript, strong RESTful API design - AI & agents: LLM integration, RAG and vector databases, agent frameworks, multi-agent orchestration, MCP and agent infrastructure, prompt engineering, context and memory management, evaluation and guardrails
We are a startup digital agency, and no two projects, clients, or even days look the same. But all of our days are agentic-first. In ecommerce we build on Shopify and Liquid and Next.js, with custom AWS microservices and apps that take Shopify well past the defaults. On the marketing side we build highly customised sites in Next.js and React, with careful design and animation and a real focus on how the page performs and feels.
- Testing & quality: automated testing, evaluation harnesses, observability and monitoring of AI systems - Cloud & infrastructure: cloud platforms, containerisation with Docker and Kubernetes, CI/CD (infrastructure-as-code with Terraform a plus) - AI tooling: Claude Code, Cursor, Copilot, Google Antigravity
In ecommerce we build on Shopify and Liquid and Next.js, with custom AWS microservices and apps that take Shopify well past the defaults. On the marketing side we build highly customised sites in Next.js and React, with careful design and animation and a real focus on how the page performs and feels. In automotive and other industries we build full platforms, AI tools and integrations, from stock-car locators to configurators and a lot more.

Your next step

Complete your application on oh-so.jobs.personio.com. The employer’s form will show what is required.

Applying through Personio

  • No account needed. The 20 MB limit covers all your files together, not each one.

Already applied? Track this application

Job description

View original posting ↗

What to expect

We are a startup digital agency, and no two projects, clients, or even days look the same. But all of our days are agentic-first.


In ecommerce we build on Shopify and Liquid and Next.js, with custom AWS microservices and apps that take Shopify well past the defaults.

 

On the marketing side we build highly customised sites in Next.js and React, with careful design and animation and a real focus on how the page performs and feels. 


In automotive and other industries we build full platforms, AI tools and integrations, from stock-car locators to configurators and a lot more.


Across all of it, we bring AI into the work through our own products.


Here nothing will be fixed. You will work across changing projects and settings, on long builds that run for months and shorter spikes to figure out how a business can actually use AI, and you will help us rethink how agency work is done.

Sound like your kind of place? Here is what we need from you.


Your competencies

We're looking for engineers who are excited by agentic and AI-native systems - turning models into products that hold up under real users, real load, and real time. You'll build LLM integrations, agents, and RAG pipelines, treat prompt engineering as a code discipline, and make systems reliable through evaluation, guardrails, and solid testing. Whether you're building your craft or already shaping the AI architecture of a project, we want to hear from you. We hire across levels - here's what each looks like at OH-SO:


Junior AI/Agentic Engineer


You're building your engineering craft - curious about why and how things work, not afraid to get your hands dirty, and eager to grow. You implement from clear briefs - LLM integrations, prompt scaffolding, RAG components - and write the tests and evaluations that keep them honest, comfortable using AI coding tools (Claude Code, Cursor, Copilot) under supervision. You want to understand why and how we're building things, ask what the purpose and the constraint are before you start, and your work is reviewed before it merges.


AI/Agentic Engineer (typically 2-3+ years) 


You own an AI feature end-to-end - an agent flow, a RAG pipeline, an integration across its error paths and guardrails - delivered independently with light oversight. You build evaluation harnesses to prove quality rather than assume it, use AI coding tools autonomously in production, and contribute to the shared AI backbone (the AI-brain MCP and skill library).


Senior AI/Agentic Engineer (typically 5+ years) 


You own the AI outcome of a project - you define the integration shape, the multi-agent architecture and orchestration, the evaluation strategy and guardrails, and you write the ADRs that document why. You're the technical credibility in the room, contribute patterns and skills back to the shared backbone, and mentor the engineers around you. You use AI to define new ways of working, and you think in long runtime: the AI landscape will shift underneath the project, so you build for inheritance and replaceable layers. You help us move forward as an organization and you act as an AI evangelist.


What you bring to the table, at any level:

  • Experience building with LLMs or AI systems in production - integration, agents, RAG, or similar

  • Strong software engineering fundamentals in Python and/or TypeScript, and confidence designing and working with APIs

  • A habit of treating prompt engineering as a code discipline — with a real understanding of evaluation, guardrails, and reliability

  • A solid grasp of testing and quality: you build systems that hold up under real use, not just in a demo

  • A genuine interest in agentic systems and where the AI landscape is heading - and the judgement to apply it well, not just talk about it

  • Openness to collaborating with cross-functional teams - from designers to strategists - as well as directly with clients

  • You’re enjoying being part of a team, not a remote desk which prefers to work in isolation most of the time.


What You Can Look Forward To

The stack you’ll work with:

  • Languages & core: Python and/or TypeScript, strong RESTful API design

  • AI & agents: LLM integration, RAG and vector databases, agent frameworks, multi-agent orchestration, MCP and agent infrastructure, prompt engineering, context and memory management, evaluation and guardrails

  • Testing & quality: automated testing, evaluation harnesses, observability and monitoring of AI systems

  • Cloud & infrastructure: cloud platforms, containerisation with Docker and Kubernetes, CI/CD (infrastructure-as-code with Terraform a plus)

  • AI tooling: Claude Code, Cursor, Copilot, Google Antigravity

Who you will work with

We are a bunch of colleagues originally from similar backgrounds who got tired of how things were usually done and set out to find better ways. That is the whole reason this company exists, and it is still what we are doing.

We are not a place of rockstars and egos. People here ask questions out loud, show rough work without flinching, and would rather help each other get something right than look clever alone. We push each other, in the good way, and we do not take ourselves too seriously while we are at it.

You would be joining that. You’ll work closely with the crafts, designers and strategists, and just as easily with the people steering the projects and the business. There is no wall between you and any of it. Take on the parts you are ready for, and when you want more, a pitch, a client conversation, a bigger call, speak up at the right moment and the door is open.

Smaller team. More ownership. Bigger work.


We are looking forward to meet you

Demand for AI Engineer roles

New AI Engineer postings at the employers we follow are up 340% over the last 6 weeks compared with the 6 before.

Weekly new AI Engineer postings at the same employers, from the week of August 17 to the week of November 9. The fewest in a week was 78, the most 803, and the latest week had 438.
August 17Last week

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.

Source details

View original posting ↗

Source notes

Source excerpts

Selected 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

Remote Germany, Prague, Hamburg, Berlin, München

- Openness to collaborating with cross-functional teams - from designers to strategists - as well as directly with clients - You’re enjoying being part of a team, not a remote desk which prefers to work in isolation most of the time. What You Can Look Forward To
Work authorization

No clear work-authorization passage found. Eligibility is unconfirmed.

Find answers in the posting

AI
How answers work

AI selects complete passages from this posting. Check them for conditions and exceptions.

Uses this posting and your question. No profile needed.