Hoppa till huvudinnehållet
WeQuel AB logo

AI Integration Engineer (MCP/API)

WeQuel AB
  • OrtStockholm
  • OmfattningHeltid
  • Sista ansökan30 dagar kvar
  • Publicerad20 nov.

Om tjänsten

WeQuel is looking for an AI Integration Engineer for an assignment with one of our clients. Agents are only as useful as the

systems they can reach – you will expose business systems as secure, well-designed tools that AI agents can use in production.

About the assignment

Workload: 100%
Location: Hybrid
Language: English

Your responsibilities

  • Build and maintain MCP servers and APIs that give agents controlled access to enterprise systems (ERP, EDI, PLM, ticketing,

document stores)

Design tool interfaces with clear schemas, error handling and least-privilege access
Implement authentication, authorisation and audit logging for agent actions
Work with agent developers to make tools reliable, fast and easy for models to use
Document integrations and contribute to shared integration patterns

Requirements

At least 4 years of experience in integration or backend development
Strong experience with REST/GraphQL APIs, event-driven integration and message queues
Solid programming skills in Python, TypeScript, C# or Java
Experience with OAuth2/OIDC and secure API design
Fluent English, written and spoken

Meritorious

Hands-on experience with the Model Context Protocol (MCP) or LLM function calling
Experience with SAP, EDI or PLM integrations
Azure API Management, Azure Integration Services or similar
Background in industrial or manufacturing environments
Swedish

Who you are

You are a structured and security-minded developer who likes to build robust building blocks that others depend on. You are

curious about AI and enjoy working closely with both agent developers and system owners.

Applications are reviewed continuously – apply today!

AI EVALUATION & QUALITY ENGINEER

WeQuel is looking for an AI Evaluation & Quality Engineer for an assignment with one of our clients. You will make sure agentic

workflows are measured honestly before and after they reach production – so the organisation knows what works, what does not, and

why.

About the assignment

Workload: 100%
Location: Hybrid
Language: English

Your responsibilities

Design evaluation strategies and quality metrics for LLM agents (accuracy, task success, safety, cost, latency)
Build and maintain evaluation datasets, test cases and automated regression tests
Set up LLM-as-judge and human review processes where needed
Run red-teaming and robustness tests, including prompt injection scenarios
Monitor agent quality in production and feed findings back to development teams
Report results clearly to product owners and stakeholders

Requirements

At least 3 years of experience in test automation, QA engineering or data science
Hands-on experience evaluating LLM or ML solutions
Strong Python skills
Understanding of statistics and experiment design
Fluent English, written and spoken

Meritorious

Experience with evaluation and observability tools (e.g. Langfuse, LangSmith, Ragas, DeepEval, promptfoo)
Experience with CI/CD pipelines for ML or LLM applications
Knowledge of AI safety and the EU AI Act
Background in industrial or manufacturing environments
Swedish

Who you are

You are analytical, sceptical in a constructive way and thorough. You enjoy finding where things break, explain results in plain

language, and help teams make better decisions based on evidence.

Applications are reviewed continuously – apply today!

Inte redo att söka direkt? Spara annonsen så skickar vi en påminnelse 3 dagar före sista ansökningsdag.

Synka i iPhone-appen →

Restid & pendling

Krav- & nyckelordscheck

Efterfrågade kompetenser – klicka på det du kan:

Anpassa ett gratis CV direkt mot annonsens kravprofil.Matcha & bygg CV för tjänsten

Representerar du WeQuel AB? Lyft fram annonsen i Stockholm och dölj konkurrerande jobb.