Autonomous AI Agent Engineer for Scalable Enterprise Ops

Orbio AI; Madrid; Sur place; EUR 90 000 - 120 000; Plein temps

Résumé du poste

Orbio is an AI-native human capital management platform building a Digital Workforce for HR. We design and deploy agentic systems that take ownership of operational execution across hiring, onboarding, and employee operations — while keeping humans in control.

Orbio is looking for an AI Agent Engineer to build, operate, and continuously improve the reliability of our agentic AI systems in production. In this role you will focus on how agents behave, decide, fail, recover, and scale in real

Qualifications

• Building agent evaluation pipelines (consistency, accuracy, reliability)
• Designing test harnesses for non-deterministic systems
• Regression testing for prompt and model changes
• Synthetic data generation for agent testing
• Performance benchmarking and latency profiling
• Observability for agent systems (tracing, logging, metrics)
• Cost tracking and optimization across model calls
• Alerting on agent failures, hallucinations, and degraded performance
• Debugging complex multi-step agent behaviors in production
• Guardrails, safety layers, and graceful degradation strategies
• Prompt engineering, chaining, and caching strategies
• RAG pipelines and vector databases
• Model selection, fine-tuning, and cost optimization
• Understanding of evaluation metrics and benchmarks
• Async programming, Django/Channels, real-time ASGI
• Production-grade application development
• Message queues (Celery + Redis) and high-throughput systems
• Testing, logging, and performance optimization
• Voice pipelines: STT, TTS, turn-taking, interruption handling
• Telephony integration (Twilio) with latency optimization
• Conversation flow design and fallback strategies
• Frontend experience (React preferred)
• CI/CD pipelines and cloud deployment (AWS/GCP)
• Deploying and operating AI systems in production

Responsabilités

• Build, operate and improve the reliability of agentic AI systems in production
• Focus on how agents behave, decide, fail, recover, and scale in enterprise environments
• Ensure agents are observable, testable, cost-efficient, and trustworthy across workflows
• Help build an end-to-end, production-grade B2B platform with LLMs and autonomous agents
• Contribute to the technical foundations that scale across customers and use cases

Connaissances

Agent evaluation

Test harnesses

Regression testing

Synthetic data

Performance benchmarking

Observability

Cost optimization

Alerting

Debugging

Guardrails

Prompt engineering

RAG pipelines

Model selection

Evaluation metrics

Async programming

Django/Channels

Message queues

Testing/logging

Performance optimization

Frontend React

CI/CD

Cloud deployment

Production deployment

Voice pipelines

Twilio integration

Conversation design

Outils

Celery

Redis

Twilio

React

Django/Channels

AWS

GCP

Description du poste

Orbio is an AI-native human capital management platform building a Digital Workforce for HR. We design and deploy agentic systems that take ownership of operational execution across hiring, onboarding, and employee operations — while keeping humans in control.

Orbio is looking for an AI Agent Engineer to build, operate, and continuously improve the reliability of our agentic AI systems in production. In this role you will focus on how agents behave, decide, fail, recover, and scale in real