About CodeRoad

CodeRoad provides end-to-end software development services, helping businesses scale with ideal infrastructure solutions. From staff augmentation to dedicated IT teams and general software engineering, our nearshore technology services empower businesses to thrive in an ever-evolving digital landscape

About the Role

As an Intermediate Agentic AI Developer, you will serve as the technical backbone of our AI engineering PODs, designing, building, and deploying production-ready AI agents and agentic workflows. You will focus on orchestrating autonomous systems using leading LLM frameworks, Retrieval-Augmented Generation (RAG), and Model Context Protocol (MCP) to seamlessly connect AI capabilities with client software ecosystems and enterprise data sources.

This role is critical to transforming business requirements into scalable, secure, and reliable agentic AI solutions on AWS. Working under the guidance of senior technical leaders, you will take ownership of core agent components, building robust evaluation pipelines, establishing security guardrails, and driving continuous improvement across the full AI development lifecycle.

Key Responsibilities

• Design & Build: Develop production-grade AI agents, state management mechanisms, and multi-agent workflows using frameworks such as LangGraph, CrewAI, or Agent Development Kit (ADK).

• Integrate & Orchestrate: Connect AI agents to enterprise tools, APIs, and external platforms via Model Context Protocol (MCP) and structured function calling.

• Optimize Knowledge Retrieval: Implement and maintain high-performance RAG pipelines using vector databases like Pinecone or Weaviate, applying semantic search, chunking, and grounding strategies.

• Evaluate & Secure: Execute automated evaluations, regression testing, task-success metrics, and safety guardrails to defend against prompt injection and sensitive-data exposure.

• Deploy & Monitor: Deploy LLM applications on AWS utilizing Amazon Bedrock, while leveraging observability platforms such as LangSmith, Langtrace, or AgentOps to troubleshoot failures and optimize performance.

• Collaborate & Maintain: Write clean, maintainable, and testable Python code, maintaining comprehensive technical documentation while collaborating with senior engineers, MLOps, and product teams.

Requirements

• Experience: 3+ years of professional software development experience, with direct, hands-on experience building LLM-based, RAG, or agentic AI applications.

• Tech Stack: Advanced Python, AWS (Amazon Bedrock), agentic frameworks (LangGraph, CrewAI, or ADK), Vector DBs (Pinecone, Weaviate), and Model Context Protocol (MCP).

• Observability & Testing: Hands-on experience testing, evaluating, and monitoring LLM execution using tools like LangSmith, Langtrace, or AgentOps.

• Soft Skills: Ownership mindset, strong troubleshooting capabilities, and a collaborative approach to delivering quality software within cross-functional teams.

• Language Skills: Advanced English (written and spoken) is mandatory.

Nice to Have

• Exposure to multi-agent systems and reinforcement learning concepts.

• Experience building front-end AI interfaces using Chainlit, Streamlit, or React.

• Familiarity with MLOps platforms like MLflow or Kubeflow.

• Exposure to secondary cloud ecosystems such as Azure AI or Google Cloud Platform (GCP).

What You’ll Love

• 100% Remote: Work from anywhere in Latin America.

• Holidays Off: Observe local national holidays.

• Paid Time Off: Generous PTO policies for rest and personal time.

• Health Insurance Assistance: Financial support for your healthcare coverage.

• Competitive USD Compensation: Earn top-tier market rates pegged to the US Dollar.

• Growth Opportunities: Continuous career evolution within high-impact global projects.