Senior AI Platform Engineer – Agentic Systems (Hybrid)

sa.global; Porto; Híbrido; EUR 90 000 - 130 000; Tempo integral

Resumo da oferta

sa.global Labs – Core Team is seeking a Senior AI Product Engineer to own the reasoning core of empower, our agentic AI platform. You will design agent orchestration, prompt architecture, and evaluation systems that translate complex agent behavior into trusted automation for real clients.

You'll work with LangGraph, DSPy, LlamaIndex, PostgreSQL with pgvector/pg_search, Neo4j, MLflow, and Prefect to build and deploy production-grade workflows.

Qualificações

• 5+ years of backend software development; Python as the primary language for AI-adjacent work.
• Proven track record of designing and shipping production APIs and distributed services, not just prototypes.
• Hands-on experience integrating LLM/AI APIs (Anthropic, OpenAI, or open-weight models via vLLM/Ollama) into real applications.
• Working knowledge of retrieval architectures built on PostgreSQL with pgvector and pg_search (production stack).
• Familiarity with MCP (Model Context Protocol) for exposing tools and data to AI agents.
• Comfort with cloud-native deployment (Azure preferred) and CI/CD.
• Daily, hands-on use of Claude Code or a comparable AI coding agent for scaffolding, refactoring, and test generation.
• Deep experience with LangGraph or a similar agent-orchestration framework.
• Working knowledge of LlamaIndex for building retrieval pipelines over enterprise data.

Responsabilidades

• Design and implement multi-agent workflows and orchestration graphs using LangGraph.
• Apply DSPy or comparable declarative prompt-programming approaches for systematic prompting, testing, and optimization.
• Build and maintain evaluation harnesses tracked in MLflow that measure accuracy, faithfulness, latency, and instruction-following across model/prompt versions.
• Architect agent memory, tool-calling, guardrails, and human-in-the-loop controls for production agent workflows serving real client decisions.
• Prototype retrieval architectures on top of the Neo4j-backed Business Knowledge Graph (GraphRAG) with LlamaIndex and pgvector/pg_search; collaborate with Level I engineers.
• Push technical judgment calls on when an agentic pattern is warranted versus when a simpler deterministic path is the right call.

Conhecimentos

Python

Backend design

APIs & microservices

LangGraph

LlamaIndex

DSPy

Neo4j

PostgreSQL pgvector

MLflow

Cloud deployment

CI/CD

Claude Code AI coding

Ferramentas

LangGraph

DSPy

LlamaIndex

PostgreSQL with pgvector/pg_search

Neo4j

MLflow

Prefect

Descrição da oferta de emprego

sa.global Labs – Core Team is seeking a Senior AI Product Engineer to own the reasoning core of empower, our agentic AI platform. You will design agent orchestration, prompt architecture, and evaluation systems that translate complex agent behavior into trusted automation for real clients.

You'll work with LangGraph, DSPy, LlamaIndex, PostgreSQL with pgvector/pg_search, Neo4j, MLflow, and Prefect to build and deploy production-grade workflows.