Job Description

Job Description
Seeking a dedicated full-time Generative AI Engineer, who will master the end-to-end lifecycle of Generative AI functions and drive MVPs into reliable, secure, and cost-effective production services in Azure. The person will report to the IT leader and will have the opportunity to influence the architecture and future hires, working as a senior collaborator.
Responsibilities:
Master the end-to-end lifecycle of generative AI functions, bringing MVPs to reliable, secure, and profitable production services in Azure.
Implement features such as document summary and question and answer chat (RAG).
Develop MLOps in Azure, including deployment, monitoring and observability.
Establish best practices for evaluating, protecting, and recording requests and responses with secure PII redaction.
Act as a hands-on expert and first full-time dedicated AI engineer, reporting to the IT leader.
Influence architecture and future hires, working as a senior collaborator.
Requirements:
5+ years of experience in MLOps and data in SaaS and cloud environments with production systems deployed.
2+ years of specific experience in generative AI (LLM, prompt engineering, retrieval augmented generation, etc.).
Proven RAG delivery with production-grade assessments (automated and targeted human review), observability (traces, prompt logging, and responses with secure PII redaction), and safeguards (cue injection and jailbreak mitigations).
Solid knowledge of Python and Docker.
Experience with MLflow.
Experience with Azure (Azure OpenAI or compatible) and vector index solutions (Azure AI Search, pgvector, Elastic).
Experience with asynchronous orchestration.
High sense of ownership, ability to challenge assumptions with data.
Strong communicator in English and able to thrive in a multifunctional and remote environment.
Experience with Databricks, Ray or Kedro is a plus.
You must be eligible to work in Portugal (EU citizen or with a valid Portuguese work permit).

Salary to receive
To agree