Role Overview
Deploy and optimize AI agent platform for SMB clients. Build workflows, integrate with business systems, and ensure customer success through hands-on technical delivery.
Key Responsibilities
- Build AI agent workflows using n8n or equivalent platforms
- Deploy Rosa's multi-agent system on customer sites
- Configure integrations with CRM, ERP, and business software
- Implement RAG systems for customer knowledge bases
- Troubleshoot on-premise NVIDIA DGX Spark deployments
- Provide technical support and training to customers
- Document solutions and best practices
- Collaborate in agile sprints
Required Qualifications
- 3+ years in AI/ML engineering or workflow automation
- Strong hands-on experience with n8n or equivalent workflow tools
- Working knowledge of LLMs and prompt engineering
- Python programming proficiency
- Experience with API integrations
- Customer-facing technical skills
- Self-starter with remote work discipline
Preferred Qualifications
- NVIDIA hardware familiarity (GPUs, deployment)
- On-premise software deployment experience
- RAG implementation knowledge
- Docker/containerization experience
- Prior work with agentic AI systems
- Experience in startup or high-growth environments
Technical Stack You'll Work With
- NVIDIA DGX Spark hardware
- OnDemand AI Operating System
- n8n or equivalent workflow automation
- Local and cloud LLMs
- Vector databases and embeddings
- Business software APIs
What We Offer
- Competitive salary (TBD based on experience)
- Fully remote, global team
- Hands-on with latest AI technology
- Career growth into lead roles
- Professional development budget
- Flexible working hours