About this role
AI Integration Engineer (MCP/API)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 assignmentWorkload: 100%Location: HybridLanguage: EnglishYour responsibilitiesBuild 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 accessImplement authentication, authorisation and audit logging for agent actionsWork with agent developers to make tools reliable, fast and easy for models to useDocument integrations and contribute to shared integration patternsRequirementsAt least 4 years of experience in integration or backend developmentStrong experience with REST/GraphQL APIs, event-driven integration and message queuesSolid programming skills in Python, TypeScript, C# or JavaExperience with OAuth2/OIDC and secure API designFluent English, written and spokenMeritoriousHands-on experience with the Model Context Protocol (MCP) or LLM function callingExperience with SAP, EDI or PLM integrationsAzure API Management, Azure Integration Services or similarBackground in industrial or manufacturing environmentsSwedishWho you areYou 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 EngineerWeQuel 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 assignmentWorkload: 100%Location: HybridLanguage: EnglishYour responsibilitiesDesign evaluation strategies and quality metrics for LLM agents (accuracy, task success, safety, cost, latency)Build and maintain evaluation datasets, test cases and automated regression testsSet up LLM-as-judge and human review processes where neededRun red-teaming and robustness tests, including prompt injection scenariosMonitor agent quality in production and feed findings back to development teamsReport results clearly to product owners and stakeholdersRequirementsAt least 3 years of experience in test automation, QA engineering or data scienceHands-on experience evaluating LLM or ML solutionsStrong Python skillsUnderstanding of statistics and experiment designFluent English, written and spokenMeritoriousExperience with evaluation and observability tools (e.g. Langfuse, LangSmith, Ragas, DeepEval, promptfoo)Experience with CI/CD pipelines for ML or LLM applicationsKnowledge of AI safety and the EU AI ActBackground in industrial or manufacturing environmentsSwedishWho you areYou 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!