Senior Agentic AI Engineer
CodeRoad · Remote · US, Latin America only
First recorded by Psst: 12 October 2026. Sign in with Google to continue to the employer. A free account is enough.
Job details
- Where you can work
- United States, Mexico, Brazil, Argentina, Colombia, Chile, Peru, Costa Rica, Uruguay, Ecuador, Dominican Republic, Guatemala, Panama, Venezuela, Bolivia, Paraguay, El Salvador, Honduras, Nicaragua
- Employment type
- Not stated by the employer
- Advertised pay
- Not stated by the employer
- Experience
- Senior
- Employer publication date
- 19 August 2026
- First recorded by Psst
- 12 October 2026
- Last checked at the source
- 30 October 2026
About the job
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 t he Role
As a Senior Agentic AI Developer, you will serve as the technical backbone of our AI engineering initiatives, designing, building, and deploying production-ready AI agents and agentic workflows. You will architect autonomous systems leveraging cutting-edge LLM frameworks, Retrieval-Augmented Generation (RAG), and Model Context Protocol (MCP) to seamlessly connect AI agents with complex enterprise infrastructures and data ecosystems.
This role is critical to transforming business requirements into scalable, secure, and highly reliable agentic solutions on AWS. You will anchor technical execution and architectural strategy, establishing robust evaluation, observability, and human-in-the-loop guardrails while guiding nearshore development teams through the entire lifecycle of production AI deployment.
Key Responsibilities
•
Architect & Build: Design, develop, and scale autonomous agentic workflows and multi-agent systems using LangGraph, CrewAI, or Agent Development Kit (ADK).
•
Anchor Cloud Infrastructure: Own the cloud deployment and security architecture of LLM-powered applications on AWS, using Amazon Bedrock and scalable microservices.
•
Integrate & Orchestrate: Connect AI agents to enterprise APIs, data sources, and deterministic tools via Model Context Protocol (MCP) and workflow platforms like n8n.
•
Optimize Knowledge Systems: Build high-performance RAG pipelines and vector database integrations using Pinecone or Weaviate to optimize contextual retrieval and reranking.
•
Evaluate & Secure: Implement end-to-end evaluation, guardrails, and security measures—including task-success metrics, hallucination checks, and protection against prompt injection.
•
Monitor & Mentor: Lead system observability using tools like LangSmith, Langtrace, or AgentOps while mentoring engineering PODs in Python and AI development best practices.
Requirements
•
Experience: 5+ years in professional software engineering, with 2–3+ years dedicated to LLM application engineering and agentic AI systems.
•
Tech Stack: Advanced Python , AWS ( Amazon Bedrock ), LangGraph / CrewAI, Vector DBs ( Pinecone , Weaviate ), RAG architecture, and MCP integration.
•
Observability & Eval Tools: Hands-on experience with LangSmith , Langtrace , or AgentOps , along with evaluation frameworks for LLM groundedness and accuracy.
•
Soft Skills: Strong ownership mindset , technical leadership, and the ability to mentor developers and articulate complex architecture to non-technical stakeholders.
•
Language Skills: Advanced English (written and spoken) is mandatory.
Nice to Have
•
Exposure to reinforcement learning and advanced multi-agent coordination architectures.
•
Hands-on experience building user-facing AI interfaces with Chainlit , Streamlit , or React .
•
Multicloud experience with 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.
- Open 10 weeks
- Reposted
- No pay listed
A resume that gets past the first 6 seconds
Recruiters skim. The Psst resume coach fixes what makes them skip you, line by line. Premium then shapes it for the exact job you're applying to.
- 1Every line checkedWeak starts, clichés and AI-sounding phrases flagged, with a 3-question fix.
- 2Tailored to the jobSee which skills and tools from the ad your resume is missing. Try it free on one of your matches.
- 3Ready for remoteTime zone, tools and proof you work on your own, the things remote teams look for.
- 4Looks the partOne page and an ATS-safe PDF, free. Premium adds 6 designs, 8 colours and a matching cover letter.
Example with made-up details. The score is the builder's own check, not an ATS rating or a promise of an interview.