platform engineer for enterprise AI platforms

Syone provides IT services and consulting, supporting innovative technology projects for national and international clients.

• Design and operate an enterprise AI platform layer integrating multiple LLM providers in production;
• Build reusable AI services and APIs for agents, copilots, and business applications;
• Manage context, memory architectures, structured outputs, and function calling;
• Optimize inference performance and manage cost attribution and usage analytics;
• Manage AI environments, including prompt and model versioning and deployment pipelines;
• Design and deploy autonomous agents and multi-agent systems for real business workflows;
• Build multi-agent orchestration using Model Context Protocol and agent collaboration frameworks;
• Develop tool-using agents with function calling, plugin architectures, and enterprise system integrations;
• Build AI copilots with Microsoft Copilot Studio;
• Automate workflows connecting AI agents to SharePoint, Salesforce, M365, and other enterprise platforms;
• Build enterprise retrieval capabilities on the Corporate Brain data platform;
• Implement hybrid search with vector indexing and Azure AI Search;
• Develop context retrieval, citation frameworks, and prompt orchestration for grounded outputs;
• Implement chunking strategies, embedding pipeline consumption, and knowledge grounding;
• Evaluate RAG performance through precision, recall, hallucination detection, and context relevance testing;
• Own the quality and safety standards for production AI systems;
• Build evaluation frameworks for accuracy, hallucination detection, and response quality;
• Implement prompt regression testing, agent benchmarking, and safety testing across model updates;
• Design and implement guardrails for input/output filtering and content policy enforcement;
• Monitor latency, cost per query, error rates, and agent task completion rates in production;
• Govern the AI lifecycle through structured approval gates before production deployment.

• 8+ Years of software engineering experience, including at least 3 years building and shipping production AI applications;
• Proven experience deploying enterprise LLM solutions used by real end-users at scale;
• Experience designing multi-agent systems and agentic orchestration architectures;
• Experience integrating AI into business workflows, not only standalone demos;
• Strong knowledge of LLM APIs and prompt engineering;
• Experience with Retrieval Augmented Generation (RAG);
• Experience building AI agents and agentic workflows;
• Knowledge of function calling and structured outputs;
• Experience with vector databases and semantic search;
• Proficiency in Python;
• Experience with REST APIs, Docker, Git, and CI/CD;
• Experience with Azure and cloud-native development;
• Experience with multi-provider LLM integration;
• Experience with AI evaluation and safety frameworks;
• Nice to have: LangGraph, Semantic Kernel, LangChain or LlamaIndex, AutoGen / CrewAI, observability platforms such as Datadog and Grafana, AI governance frameworks, advanced Azure AI Search, fine-tuning or RLHF experience.

• Professional development through participation in ambitious national and international technology projects;
• Strong IT training plans;
• The role is based in Lisbon, Portugal.