About this role
Developers who thrive when owning core agent components and orchestrating autonomous systems will find a strong fit at CodeRoad. The engineering team builds production-ready AI agents, state management mechanisms, and multi-agent workflows to help businesses scale their infrastructure.
Working within dedicated AI engineering PODs, this person focuses on connecting AI capabilities with enterprise data sources using leading LLM frameworks, Retrieval-Augmented Generation, and Model Context Protocol. The role exists to transform complex business requirements into scalable, secure, and reliable agentic AI solutions on AWS, requiring individuals who can write clean Python code and build robust evaluation pipelines under the guidance of senior technical leaders.
What you will do
- Design and develop production-grade AI agents, state management mechanisms, and multi-agent workflows using frameworks such as LangGraph, CrewAI, or Agent Development Kit.
- Connect AI agents to enterprise tools, APIs, and external platforms via Model Context Protocol and structured function calling.
- Implement and maintain high-performance RAG pipelines using vector databases with semantic search, chunking, and grounding strategies.
- Execute automated evaluations, regression testing, task-success metrics, and safety guardrails to defend against prompt injection and sensitive-data exposure.
- Deploy LLM applications on AWS utilizing Amazon Bedrock while leveraging observability platforms to troubleshoot failures and optimize performance.
- Write clean, maintainable, and testable Python code while maintaining technical documentation and collaborating with senior engineers, MLOps, and product teams.
What you need
- Bring at least three years of professional software development experience with direct, hands-on work building LLM-based, RAG, or agentic AI applications.
- Demonstrate advanced proficiency in Python and familiarity with AWS services like Amazon Bedrock.
- Utilize agentic frameworks such as LangGraph, CrewAI, or ADK alongside vector databases like Pinecone or Weaviate.
- Possess hands-on experience testing, evaluating, and monitoring LLM execution using tools like LangSmith, Langtrace, or AgentOps.
- Demonstrate an ownership mindset, strong troubleshooting capabilities, and a collaborative approach within cross-functional teams.
- Communicate effectively with mandatory advanced English skills in both written and spoken formats.
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
Benefits
- 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.
Skills and tech stack
Questions candidates ask
What is the remote work policy for this position?
The role is 100% remote, allowing team members to work from anywhere in Latin America.
How is compensation structured?
Compensation offers top-tier market rates pegged to the US Dollar.
What tools and frameworks will I use daily?
Daily work involves advanced Python, AWS with Amazon Bedrock, agentic frameworks like LangGraph or CrewAI, vector databases, and Model Context Protocol.
What kind of team support and growth can I expect?
You will work under the guidance of senior technical leaders within AI engineering PODs, with continuous career evolution supported across high-impact global projects.