Python Engineer (With Langgraph)

Intellias; Viseu; Presencial; EUR 50 000 - 90 000; Tempo integral

Resumo da oferta

A Intellias procura um Engenheiro Python para construir e manter fluxos de trabalho de agentes com Lang Graph, focando em orquestração, checkpointing, interações human-in-the-loop, padrões de resiliência e observabilidade.

A função envolve colaborar com equipas de IA e plataforma para projetar soluções escaláveis, testando cenários de recuperação e assegurando desempenho confiável em um ecossistema de software de IoT e comércio digital.

Qualificações

• Mais de 4 anos de experiência em desenvolvimento Python.
• Experiência prática com Lang Graph ou Lang Chain para orquestração de agentes.
• Experiência com design de fluxos de trabalho assíncronos e distribuídos.
• Experiência em HITL (Human-in-the-Loop) e monitorização.
• Familiaridade com tracing OpenTelemetry em diferentes camadas de orquestração.

Responsabilidades

• Projetar e implementar fluxos de trabalho de agentes de IA usando Lang Graph e Python.
• Construir e manter lógica de orquestração baseada em grafos com transições de estado.
• Imple­mentar checkpoints e recuperação usando SQLite, Redis ou PostgreSQL.
• Desenvolver fluxos HITL para aprovações, escalonamento e intervenção.
• Implementar execução assíncrona de workflows com Python asyncio.
• Garantir observabilidade com OpenTelemetry nas etapas de orquestração.

Conhecimentos

Python

Lang Graph / Lang Chain

Async/Await

Distributed workflows

HITL

OpenTelemetry tracing

Testing workflows

SQL backends (SQLite/Redis/PostgreSQL)

Ferramentas

Lang Graph

Lang Chain

OpenTelemetry

SQLite

Redis

PostgreSQL

AWS Bedrock

Descrição da oferta de emprego

Descrição do cargo

We are looking for a Python Engineer to build and maintain stateful AI agent workflows using Lang Graph. The role focuses on workflow orchestration, checkpointing, human‑in‑the‑loop interactions, resilience patterns, and observability across agent execution paths. The ideal candidate has strong Python expertise, hands‑on experience with Lang Graph or Lang Chain, and a solid understanding of asynchronous and distributed workflow design.

Project Overview: Our customer is a multinational corporation with more than a century of history and offices in over 180 countries. Their most ambitious goal at the time is to introduce a range of Reduced‑Risk Products (RRPs). The target audience is more than 1 billion consumers around the globe. IT platform hosts 700+ applications. Intellia's mission is to help the client with the engineering of a comprehensive software ecosystem for a game‑changing Io T product on the margin of innovative consumer experience and cutting‑edge technology.

Our teams are involved in the engineering of core platform components for best‑in‑class e Commerce, Digital Marketing and Io T solutions. As an Engineer, you will become a part of Core Architecture Team and be responsible for the architecture, implementation of best practices in our Digital Engineering Enterprise Platform. The Platform is a set of services and internet applications that accelerate the development and delivery of software applications by taking care of common SDLC challenges.

The Platform provides access and consumption for engineering teams to a set of services, technologies, practices for their development and for operating their application, ensuring a set of compliance and best practices.

Requirements

Python (Lang Graph nodes, edges, graphs) Checkpointing with Lang Graph (SQLite, Redis, Postgres checkpointers) HITL workflow implementation Retry, timeout, fallback patterns in Lang Graph Open Telemetry tracing across orchestration steps Experience: 4+ years Python development Lang Graph or Lang Chain agent orchestration Will be a plus: AWS Bedrock integration Multi-agent workflow testing Lang Smith trace visualization Responsibilities: Design and implement AI agent workflows using Lang Graph and Python.

Build and maintain graph‑based orchestration logic using nodes, edges, and state transitions. Implement workflow checkpointing and recovery mechanisms using SQLite, Redis, or Postgre SQL backends. Develop Human‑in‑the‑Loop (HITL) workflows for approval, escalation, and intervention scenarios. Design resilient execution patterns including retries, timeouts, fallback handling, and failure recovery. Develop asynchronous workflow execution using Python asyncio. Implement Open Telemetry tracing across orchestration layers and workflow steps.

Troubleshoot workflow execution issues and optimize performance, reliability, and observability. Collaborate with platform and AI engineering teams to build scalable agent‑driven solutions. Create automated tests for workflow reliability, state transitions, and recovery scenarios. Contribute to engineering standards and best practices around agent orchestration and workflow management.