AI Engineer (Python/LLM Agents) - Hybrid Porto (2 days/week office) ABOUT THE OPPORTUNITY We're looking for a Senior AI Engineer to join a fast-growing, AI-driven company that turns large volumes of business registry and web data into trusted, structured intelligence. You'll be the person who takes ownership of agent-to-agent (A2A) systems from start to finish. You'll design how autonomous agents talk to each other, share context and hand off tasks reliably in production. If you want to work at the front of multi-agent LLM engineering rather than on chatbot prototypes, this role is for you. PROJECT & CONTEXT
- Build agent harnesses that manage context windows, memory and tool calls across complex, multi-step workflows
- Own agent-to-agent processes from start to finish: design the communication protocols, information exchange and task handoffs that let multiple agents work together autonomously and reliably
- Design and maintain pipelines that turn registry and web data into structured records that can be audited
- Work closely with the ML and backend teams to take prototypes into robust production systems
- Build evaluation frameworks that track data quality and LLM performance over time
- Hybrid setup in Porto (2 days/week in the office), working with an international, product-focused team WHAT WE'RE LOOKING FOR (Required)
- 5+ years of experience in software, data or ML engineering (Senior level)
- Strong Python (3.10+) skills and solid experience building backend APIs (e.g. FastAPI, Flask or Django)
- Hands-on experience with production LLM integrations (e.g. OpenAI, Anthropic or open-source models), including tool and function calling
- Proven experience designing multi-agent systems, with clear ownership of agent orchestration, inter-agent communication and task handoffs
- Experience with AI and LLM evaluation (quality metrics, regression testing, monitoring)
- Experience with data orchestration tools such as Airflow, Dagster or Prefect
- Familiarity with MLOps practices, CI/CD pipelines and cloud infrastructure (AWS, GCP or Azure)
- English: B2 (Upper Intermediate) minimum
- Based in Porto, or willing to relocate, for the hybrid model NICE TO HAVE (Preferred)
- Experience with agent frameworks such as LangGraph, CrewAI, AutoGen or the OpenAI Agents SDK
- Knowledge of agent interoperability standards such as the A2A protocol or the Model Context Protocol (MCP)
- Experience with web scraping and data extraction at scale
- Background in RegTech, compliance, KYC/KYB or business data domains
- Experience with observability tools for LLM systems (e.g. LangSmith, Langfuse, Arize)
- Containerisation and infrastructure-as-code (Docker, Kubernetes, Terraform) Compensation: €2,300 – €3,050/month net, depending on experience and seniority level. Why HumanIT people stay (4.4 Glassdoor, 89% recommend) - 15th month salary - Health insurance covering your family - Birthday off - Mobility program for digital nomads - Real work-life balance Full benefits https://www.humanit.pt/careers/#perks What it's really like https://www.humanit.pt/careers/#work-at
