python developer for HR operations

Orbio is an AI-native human capital management platform building a Digital Workforce for HR. It designs and deploys agentic systems that execute operational workflows across hiring, onboarding, and employee operations while keeping humans in control.

• Build, operate, and continuously improve the reliability of agentic AI systems in production;
• Build agent evaluation pipelines for consistency, accuracy, and reliability;
• Design test harnesses for non-deterministic systems;
• Perform regression testing for prompt and model changes;
• Generate synthetic data for agent testing;
• Benchmark performance and profile latency;
• Implement observability for agent systems through tracing, logging, and metrics;
• Track and optimize costs across model calls;
• Set up alerting for agent failures, hallucinations, and degraded performance;
• Debug complex multi-step agent behaviors in production;
• Implement guardrails, safety layers, and graceful degradation strategies;
• Develop prompt engineering, chaining, and caching strategies;
• Build RAG pipelines and work with vector databases;
• Select and fine-tune models and optimize costs;
• Develop production-grade applications with Python;
• Work with async programming, Django/Channels, and real-time ASGI;
• Build high-throughput systems using Celery and Redis;
• Implement testing, logging, and performance optimization;
• Develop voice pipelines covering STT, TTS, turn-taking, and interruption handling;
• Integrate telephony with Twilio and optimize latency;
• Design conversation flows and fallback strategies;
• Build frontend features with React;
• Develop CI/CD pipelines and cloud deployments;
• Deploy and operate AI systems in production.

• Experience with agent testing and evaluation;
• Experience designing test harnesses for non-deterministic systems;
• Experience with observability, monitoring, and production debugging;
• Knowledge of prompt engineering, chaining, caching, RAG, and vector databases;
• Understanding of model selection, fine-tuning, evaluation metrics, and benchmarks;
• Python backend development experience;
• Experience with async programming, Django/Channels, and ASGI;
• Experience with Celery, Redis, testing, logging, and performance optimization;
• Knowledge of conversational AI and voice pipelines;
• Experience with frontend development;
• Experience with CI/CD and cloud deployment on AWS or GCP;
• Nice to have: React experience.

• No conditions specified