Senior Remote Agentic AI Architect for Multi-Agent Systems

Quantiphi; United States; Remote; USD 140,000 - 190,000; Full time

Job summary

Quantiphi is seeking a Senior Machine Learning Engineer to architect, build, and deploy production-grade agentic AI systems for multi-agent workflows. You will design autonomous, collaborative agents with robust memory, tool-calling capabilities, and scalable orchestration across major cloud platforms.

You will integrate LLMs for core reasoning, implement RAG-based retrieval, and ensure observability with a strong focus on CI/CD and MLOps in a remote US environment.

Qualifications

• 6-8 years of hands-on experience in machine learning and AI engineering with production background.
• Expertise in building multi-agent systems and agentic workflows, preferably with Langraph/CrewAI.
• Proficiency in Python and ML frameworks; experience with FastAPI, async programming, and microservices.
• Hands-on with vector databases and scalable RAG systems; cloud deployment on AWS, GCP, or Azure.

Responsibilities

• Architect and build end-to-end multi-agent systems from scratch with agent harnesses.
• Develop agent-tools and agent-skills for complex domain tasks and memory systems.
• Deploy production-grade agentic solutions on major clouds and implement MLOps practices.
• Integrate and optimize LLMs as core reasoning engines for autonomous agents.
• Design RAG systems using vector databases and manage observability and monitoring.

Skills

Python

Multi-agent systems

LLM deployment

Cloud platforms

MLOps CI/CD

Langraph/CrewAI

Tools

Pinecone

Weaviate

ChromaDB

LangSmith

Weights & Biases

Job description

Quantiphi is seeking a Senior Machine Learning Engineer to architect, build, and deploy production-grade agentic AI systems for multi-agent workflows. You will design autonomous, collaborative agents with robust memory, tool-calling capabilities, and scalable orchestration across major cloud platforms.

You will integrate LLMs for core reasoning, implement RAG-based retrieval, and ensure observability with a strong focus on CI/CD and MLOps in a remote US environment.