AI Engineer

We are looking for an AI Engineer to join our Inetum Team and be part of a work culture focused on innovation!

Location:

Lisbon or Porto

Main Tasks

Design, build, and continuously improve AI agents, including their reasoning flows, tool use, prompts, and evaluation frameworks.

Develop and maintain agents in Python using LangGraph, LangChain, and an internal SDK, and adapt central general-purpose agents (drafting, summarisation, process orchestration) to custody back-office use cases.

Design agent workflows covering task decomposition, tool and function calling against APIs, memory and state handling, guardrails, and human-in-the-loop checkpoints appropriate to back-office controls.

Engineer, test, and version prompts, and manage prompt and configuration changes through Kubernetes ConfigMaps with proper release discipline.

Build and run agent evaluation using golden datasets from real back-office cases, regression suites, quality metrics (accuracy, groundedness, escalation rate), and shadow testing before rollout.

Instrument agents for observability through structured logging of reasoning traces, token usage, latency, and failure modes, and handle model lifecycle concerns including provider changes, context window constraints, and cost/latency trade-offs.

Work daily with the Business Analyst to translate operational knowledge (settlements, corporate actions, client queries, reconciliations) into agent behaviour.

Profile

3 to 6 years of Python engineering experience, with at least 1 to 2 years on LLM/GenAI applications.

Practical experience with at least one agent framework such as CrewAI, LangGraph, LangChain, or AutoGen, with understanding of ReAct-style loops, tool calling, and structured outputs.

Solid grasp of prompt engineering, RAG patterns, and LLM evaluation techniques.

Comfortable consuming REST/gRPC APIs (Go backend), JSON schema design, and async Python.

Working knowledge of Docker and Kubernetes, including deployment, log reading, and ConfigMap editing.

Strong testing culture with experience in pytest, mocking LLM calls, and deterministic test design for non-deterministic systems.

Additional Information

Hybrid work regime – office in Lisbon or Porto.

Integration into a newly created 5-person squad maintaining and evolving a portfolio of production AI agents for the securities services (custody) division of a major European bank.

Exposure to cutting-edge AI agent technologies in a complex and regulated financial environment.

Opportunities for professional growth and development.

Collaborative and innovative work environment.

#J-18808-Ljbffr