Remote Agentic AI Engineer - Growth & Impact

CodeRoad Inc; United States; Remote; USD 120,000 - 180,000; Full time

Benefits offered by this job

100% Remote

Holidays Off

Paid Time Off

Health Insurance Assistance

Competitive USD Compensation

Growth Opportunities

Job summary

CodeRoad Inc. is seeking an Intermediate Agentic AI Developer to lead production-grade AI agents and agentic workflows within our AI engineering PODs. You will design, build, and deploy scalable LLM-based solutions on AWS, integrating MCP, RAG, and multi-agent frameworks.

Working under senior engineers, you will own core components, build evaluation pipelines, enforce security guardrails, and drive continuous improvement across the AI development lifecycle while collaborating with product teams.

Qualifications

• 3+ years of professional software development experience building LLM-based, RAG, or agentic AI apps.
• Proficiency in Python and AWS Bedrock with experience in agentic frameworks (LangGraph, CrewAI, or ADK).
• Familiarity with MCP, semantic search, and evaluation/testing of AI systems.

Responsibilities

• Design & Build production-grade AI agents and multi-agent workflows.
• Integrate AI agents with enterprise tools via MCP and function calling.
• Develop high-performance RAG pipelines using vector databases.
• Run automated evaluations, testing, and safety guardrails for AI systems.
• Deploy LLM apps on AWS Bedrock and monitor performance with observability tools.
• Write clean, maintainable Python and document technical work.

Skills

Python

AWS Bedrock

LangGraph

CrewAI

ADK

RAG

MCP

Advanced English

Ownership mindset

Tools

LangSmith

Langtrace

AgentOps

Pinecone

Weaviate

Job description

CodeRoad Inc. is seeking an Intermediate Agentic AI Developer to lead production-grade AI agents and agentic workflows within our AI engineering PODs. You will design, build, and deploy scalable LLM-based solutions on AWS, integrating MCP, RAG, and multi-agent frameworks.

Working under senior engineers, you will own core components, build evaluation pipelines, enforce security guardrails, and drive continuous improvement across the AI development lifecycle while collaborating with product teams.