Staff AI Engineer

📋 Description

• Own end-to-end development of multi-agent AI systems.
• Build modular agentic systems with orchestration frameworks (LangChain) operating 24/7.
• Develop reusable agentic skills across Slack, dashboards, and CLIs.
• Implement observability, logging, metrics, prompt iteration, and cost controls.
• Establish governance for AI workflows (PII handling, access controls, human-in-the-loop).
• Architect data flows for retrieval-augmented generation (RAG) with internal data.

🎯 Requirements

• 8+ years of software engineering experience in backend, systems integration, or data/analytics.
• 2+ years applying LLMs/AI to production workflows.
• Proficiency in Python and JavaScript/Node.js with Git-based workflows and testing.
• Hands-on with LLM frameworks/patterns: prompt engineering, RAG, function calling, parsing, evaluation.
• Experience building and operating multi-agent systems at scale (orchestration, state management, production monitoring).
• Familiarity with Google Cloud Platform, BigQuery, and serverless/containerized services (Cloud Functions, Cloud Run).
• Understanding of LLM failure modes and production mitigations (confidence thresholds, fallback, human escalation, cost/latency).

🎁 Benefits

• 100% Remote, Global Culture
• Transparent communication and regular updates
• Career growth pathways and opportunities
• Open source roots that influence how we work
• Empowered teams with high-trust environment
• 30 days annual leave plus Grafana Shutdown Days (3 days)