<h3 data-path-to-node="2"><span class="citation-58 citation-59 citation-end-59">About CodeRoad</span></h3> <h3 id="p-rc_61a55d43d8f5bb58-34" data-path-to-node="2"></h3> <p id="p-rc_61a55d43d8f5bb58-35" data-path-to-node="3"><span class="citation-56 citation-57 citation-end-57">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</span><span class="citation-56 citation-end-56"> ever-evolving digital landscape</span></p> <p> </p> <h3 data-path-to-node="4"><span class="citation-55 citation-end-55">About t</span>he Role</h3> <h3 id="p-rc_61a55d43d8f5bb58-36" data-path-to-node="4"></h3> <p data-path-to-node="5">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.</p> <p data-path-to-node="6">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.</p> <h3 data-path-to-node="7">Key Responsibilities</h3> <ul data-path-to-node="8"> <li> <p data-path-to-node="8,0,0"><strong data-path-to-node="8,0,0" data-index-in-node="0">Design & Build:</strong> Develop production-grade AI agents, state management mechanisms, and multi-agent workflows using frameworks such as LangGraph, CrewAI, or Agent Development Kit (ADK).</p> </li> <li> <p data-path-to-node="8,1,0"><strong data-path-to-node="8,1,0" data-index-in-node="0">Integrate & Orchestrate:</strong> Connect AI agents to enterprise tools, APIs, and external platforms via Model Context Protocol (MCP) and structured function calling.</p> </li> <li> <p data-path-to-node="8,2,0"><strong data-path-to-node="8,2,0" data-index-in-node="0">Optimize Knowledge Retrieval:</strong> Implement and maintain high-performance RAG pipelines using vector databases like Pinecone or Weaviate, applying semantic search, chunking, and grounding strategies.</p> </li> <li> <p data-path-to-node="8,3,0"><strong data-path-to-node="8,3,0" data-index-in-node="0">Evaluate & Secure:</strong> Execute automated evaluations, regression testing, task-success metrics, and safety guardrails to defend against prompt injection and sensitive-data exposure.</p> </li> <li> <p data-path-to-node="8,4,0"><strong data-path-to-node="8,4,0" data-index-in-node="0">Deploy & Monitor:</strong> Deploy LLM applications on AWS utilizing Amazon Bedrock, while leveraging observability platforms such as LangSmith, Langtrace, or AgentOps to troubleshoot failures and optimize performance.</p> </li> <li> <p data-path-to-node="8,5,0"><strong data-path-to-node="8,5,0" data-index-in-node="0">Collaborate & Maintain:</strong> Write clean, maintainable, and testable Python code, maintaining comprehensive technical documentation while collaborating with senior engineers, MLOps, and product teams.</p> </li> </ul> <h3 data-path-to-node="9">Requirements</h3> <ul data-path-to-node="10"> <li> <p data-path-to-node="10,0,0"><strong data-path-to-node="10,0,0" data-index-in-node="0">Experience:</strong> 3+ years of professional software development experience, with direct, hands-on experience building LLM-based, RAG, or agentic AI applications.</p> </li> <li> <p data-path-to-node="10,1,0"><strong data-path-to-node="10,1,0" data-index-in-node="0">Tech Stack:</strong> Advanced <strong data-path-to-node="10,1,0" data-index-in-node="21">Python</strong>, AWS (<strong data-path-to-node="10,1,0" data-index-in-node="34">Amazon Bedrock</strong>), agentic frameworks (<strong data-path-to-node="10,1,0" data-index-in-node="71">LangGraph</strong>, <strong data-path-to-node="10,1,0" data-index-in-node="82">CrewAI</strong>, or <strong data-path-to-node="10,1,0" data-index-in-node="93">ADK</strong>), Vector DBs (<strong data-path-to-node="10,1,0" data-index-in-node="111">Pinecone</strong>, <strong data-path-to-node="10,1,0" data-index-in-node="121">Weaviate</strong>), and Model Context Protocol (<strong data-path-to-node="10,1,0" data-index-in-node="160">MCP</strong>).</p> </li> <li> <p data-path-to-node="10,2,0"><strong data-path-to-node="10,2,0" data-index-in-node="0">Observability & Testing:</strong> Hands-on experience testing, evaluating, and monitoring LLM execution using tools like <strong data-path-to-node="10,2,0" data-index-in-node="112">LangSmith</strong>, <strong data-path-to-node="10,2,0" data-index-in-node="123">Langtrace</strong>, or <strong data-path-to-node="10,2,0" data-index-in-node="137">AgentOps</strong>.</p> </li> <li> <p data-path-to-node="10,3,0"><strong data-path-to-node="10,3,0" data-index-in-node="0">Soft Skills:</strong> <strong data-path-to-node="10,3,0" data-index-in-node="13">Ownership mindset</strong>, strong troubleshooting capabilities, and a collaborative approach to delivering quality software within cross-functional teams.</p> </li> <li> <p data-path-to-node="10,4,0"><strong data-path-to-node="10,4,0" data-index-in-node="0">Language Skills:</strong> <strong data-path-to-node="10,4,0" data-index-in-node="17">Advanced English</strong> (written and spoken) is mandatory.</p> </li> </ul> <h3 data-path-to-node="11">Nice to Have</h3> <ul data-path-to-node="12"> <li> <p data-path-to-node="12,0,0">Exposure to multi-agent systems and reinforcement learning concepts.</p> </li> <