Senior Agentic AI Engineer - End-to-End Production

MethodHub; Mountain View (CA); On-site; USD 180,000 - 260,000; Full time

Job summary

MethodHub is seeking a Senior Applied AI Engineer – Agentic Systems in Mountain View, CA for long-term engagement. You will design, build, and ship autonomous, agentic features directly within EAS, including multi-step orchestration, tool-calling loops, and human-in-the-loop patterns.

You will own end-to-end delivery—architecture, implementation, testing, deployment, and maintenance—while enabling enterprise-grade reliability, observability, and scalability.

Qualifications

• Hands-on experience delivering agentic AI features in production
• Strong full-stack experience with Python/TypeScript
• Experience with RAG pipelines and memory systems
• Familiarity with agent frameworks (LangGraph, Anthropic/OPenAI SDKs)
• Ability to design evaluation harnesses and guardrails

Responsibilities

• Design, build, and ship agentic features within the product
• Own architecture, implementation, testing, and production deployment
• Create memory/state management to maintain context over long workflows
• Develop tool-calling loops, multi-step orchestration, and human-in-the-loop patterns
• Integrate agentic capabilities into existing product codebase with minimal disruption
• Build and evaluate RAG pipelines for structured/unstructured data
• Implement logging, tracing, and monitoring for production reliability

Skills

Full-stack engineering

Python

TypeScript

Agent frameworks

RAG pipelines

Memory systems

Observability

Unit testing

Tools

LangGraph

Anthropic SDK

OpenAI Agents SDK

CrewAI

AutoGen

Job description

MethodHub is seeking a Senior Applied AI Engineer – Agentic Systems in Mountain View, CA for long-term engagement. You will design, build, and ship autonomous, agentic features directly within EAS, including multi-step orchestration, tool-calling loops, and human-in-the-loop patterns.

You will own end-to-end delivery—architecture, implementation, testing, deployment, and maintenance—while enabling enterprise-grade reliability, observability, and scalability.