Description

Join the Maxta engineering team to build production-grade AI infrastructure. You will work on MaxtaOS compute scheduling, MaxModel deployment pipelines, and LangGraph-based multi-agent systems for industrial AI applications.

What You Will Do

• Build and optimize GPU resource management and scheduling algorithms
• Develop model packaging and deployment automation (MaxModel pipeline)
• Implement LangGraph multi-agent workflows for industrial AI (MaxPlant.ai)
• Integrate RAG systems with enterprise knowledge bases (RAGFlow, vector DBs)
• Write production-grade Python/Go services with comprehensive testing
• Deploy and optimize on edge hardware (NVIDIA Jetson AGX Thor)

Requirements

• 4+ years in backend/infrastructure engineering
• Strong Python skills; Go or Rust is a plus
• Experience with LLM frameworks (LangChain, LangGraph, or similar)
• Familiarity with RAG pipelines, vector databases (Qdrant, Milvus, FAISS)
• Experience with containerization and CI/CD
• Understanding of GPU computing basics

Benefits

• Competitive salary + equity
• Work on real AI infrastructure, not chatbot wrappers
• Direct access to cutting-edge hardware (Jetson Thor, RTX PRO 6000)
• Flexible remote/hybrid options
• Full benefits package

Department: Engineering; Location: Silicon Valley, CA / Remote; Type: Hybrid; Experience: Mid-Senior; Salary Range: $140K – $200K + Equity