About the Role
We are a startup digital agency focused on agentic-first AI systems. We build custom solutions on platforms like Shopify and Next.js, integrating AI tools and custom AWS microservices. Our work spans e-commerce, marketing, and various industries, with a focus on creating AI-native workflows and products that redefine brand capabilities.
Responsibilities
- Build LLM integrations, agents, and RAG pipelines.
- Treat prompt engineering as a code discipline.
- Ensure system reliability through evaluation, guardrails, and testing.
- Implement LLM integrations, prompt scaffolding, and RAG components.
- Write tests and evaluations for AI systems.
- Own an AI feature end-to-end, including error paths and guardrails.
- Build evaluation harnesses to ensure quality.
- Contribute to the shared AI backbone (MCP and skill library).
- Define the AI outcome of a project, including integration shape, multi-agent architecture, and evaluation strategy.
- Document architectural decisions (ADRs).
- Mentor other engineers.
- Define new ways of working using AI.
- Build for inheritance and replaceable layers in AI systems.
- Act as an AI evangelist.
- Collaborate with cross-functional teams, designers, strategists, project leads, and clients.
Requirements
- Experience building with LLMs or AI systems in production (integration, agents, RAG, or similar).
- Strong software engineering fundamentals in Python and/or TypeScript.
- Confidence designing and working with APIs.
- A habit of treating prompt engineering as a code discipline.
- A real understanding of evaluation, guardrails, and reliability.
- A solid grasp of testing and quality.
- A genuine interest in agentic systems and the AI landscape.
- Judgement to apply AI effectively.
- Openness to collaborating with cross-functional teams.
- Enjoy being part of a team environment.
Skills
- Python
- TypeScript
- RESTful API design
- LLM integration
- RAG and vector databases
- Agent frameworks
- Multi-agent orchestration
- MCP and agent infrastructure
- Prompt engineering
- Context and memory management
- Evaluation and guardrails
- Automated testing
- Evaluation harnesses
- Observability and monitoring of AI systems
- Cloud platforms
- Containerisation with Docker and Kubernetes
- CI/CD
- Infrastructure-as-code with Terraform
- AI tooling (Claude Code, Cursor, Copilot, Google Antigravity)
Location
- Hamburg
- Prague
- Berlin
- Munich
Work Type
- Full-time
Experience Level
- Junior
- Mid-level
- Senior
About the Company
- OH-SO is an AI-native marketing & technology agency, powered by WPP.
- We build AI-enabled teams across strategy, creative, and technology.
- Our work is divided into two tracks: Experiences (ideas, platforms, products) and Systems (AI-native workflows and delivery models).
- We build tools and capability into every client relationship.
- Founded in 2024 with a strategic minority investment from WPP.
- We have offices in Hamburg, Prague, Berlin, and Munich.
- We have access to WPP's global network of 115,000+ talent and 35,000+ tech experts.
