Remote Senior AI Systems Engineer: Agent Reliability

Mindera; Viseu; Teletrabalho; EUR 70 000 - 100 000; Tempo integral

Vantagens oferecidas por esta oferta de emprego

Health Insurance

Open holidays

Profit distribution

Mindera Annual Trip

Training & conferences

Laptop & peripherals

Unlimited hotspot

Resumo da oferta

Mindera is seeking a Senior AI Engineer for AI Systems to own the reusable accelerator core, multi-agent workflows, and the evaluation pipelines that quantify quality and detect regressions. You will design agents across coding, planning, review, and testing with tool-calling and human-in-the-loop where appropriate.

You will ensure reliability, cost control, and observability for agentic systems in production.

Qualificações

• At least 6 years of professional experience relevant for the role (probably a mix of AI Engineering and Software Deveopment).
• Can deploy a working customer facing app themselves including devops, front end, backend etc
• Has experience building a production app which was modern, could handle scale, fast, responsive etc
• AI SDLC in production experience
• Real depth in LLM application engineering: prompt design, function calling, structured outputs, RAG, vector stores, with the Anthropic and OpenAI APIs.
• Evaluation-driven development as a core habit, not an afterthought. You treat evals as the source of truth.
• Experience building agentic systems end to end: systems that plan, write code, validate their own output, and improve over time.
• Familiar with the orchestration landscape (LangGraph, LlamaIndex, AutoGen, CrewAI) and opinionated about when a thin custom harness beats a framework.
• Working fluency with at least one cloud data platform and SQL: enough to build eval and verification infrastructure that your applied-data counterpart fills with domain rules. You do not need to be the deepest data expert in the room.

Responsabilidades

• The reusable accelerator core and the multi-agent workflows built on it.
• Agent design across coding, planning, review, and testing agents, with tool-calling and human-in-the-loop where it earns its place.
• The evaluation pipelines and telemetry that make quality measurable and regressions visible.
• Reliability, cost control, and observability for agentic systems in real use.

Conhecimentos

LLM application engineering

Prompt design

Function calling

Structured outputs

RAG

Vector stores

OpenAI API

Anthropic API

Evaluation-driven development

End-to-end agentic systems

Ferramentas

LangGraph

LlamaIndex

AutoGen

CrewAI

OpenAI API

Anthropic API

Descrição da oferta de emprego

Mindera is seeking a Senior AI Engineer for AI Systems to own the reusable accelerator core, multi-agent workflows, and the evaluation pipelines that quantify quality and detect regressions. You will design agents across coding, planning, review, and testing with tool-calling and human-in-the-loop where appropriate.

You will ensure reliability, cost control, and observability for agentic systems in production.