AI Developer

AI Developer (MCP) Hey there! We're looking for an AI Developer (MCP) for a leading US-based broadband and telecom company focused on enterprise AI infrastructure and intelligent automation. If you are hands-on with AI agent engineering, experienced in building custom MCP servers with LangGraph, RAG pipelines, and production deployment, keep reading!100% Remote Salary in USD Latin America – Reporting to Phoenix, Arizona, US Central Time Full Time Fluent English — spoken and written About Our ClientYou will be working for our client, a broadband and telecommunications company that is modernizing its enterprise IT operations through AI-driven automation and agentic systems. They are building scalable AI infrastructure to support IT operations management, service automation, and intelligent data access across their organization. The team works in an agile, collaborative environment with direct stakeholder engagement and a strong focus on production-quality AI systems. About AthynaAthyna is a Global Talent Platform, helping align world-class talent with the best employment opportunities across the globe. We believe in the future of work. That's why we are a 100% globally distributed team across 5 continents. We believe in people, and we value freedom, integrity, quality, and sustainability. We're proudly carbon neutral as an organization and 5% of all revenue funds impact-driven startups & climate tech. We're very keen on social impact — we truly care about everyone on our team, and we want to make the world a better place for all of us. In Your Day-to-Day, You WillDesign and build custom MCP (Model Context Protocol) servers from scratch — including schema design, lifecycle management, and extension strategies — to enable secure, structured data access for agentic AI systems Engineer AI agents and multi-actor workflows using multiple frameworks (LangGraph, CrewAI, AutoGen, or similar), reasoning through architectural tradeoffs independently Implement and optimize RAG pipelines with vector databases for document retrieval and enterprise knowledge management Apply platform-agnostic guardrails and security controls across the full agent and tool lifecycle, including input/output filtering, data masking, and pre/post-tool execution controls Manage containerized deployments using GitOps practices — branching strategies, promotion workflows, and Git as source of truth — alongside CI/CD pipelines Work with observability and monitoring tools (Langfuse, Grafana) to track AI system performance, cost, and quality in production Integrate AI solutions with enterprise systems (ServiceNow, Redis, n8n, and similar platforms) Collaborate directly with US-based stakeholders, communicating technical requirements, architectural decisions, and delivery updates clearly in spoken and written English Skills You Have 3+ years of hands-on AI/ML development with production deployments Custom MCP server engineering — you have designed and built MCPs, not just connected agents to existing ones; you can explain MCP schemas, lifecycle management, and extension strategies with real examples Multi-framework AI agent experience — LangChain, LangGraph, CrewAI, AutoGen, or similar; you are not reliant on a single vendor ecosystem and can reason about architectural tradeoffs independently Platform-agnostic guardrails and security — concrete experience implementing input/output filtering, data masking, redaction, and pre/post-tool execution controls across different platforms GitOps fundamentals — branching strategies, promotion strategies, infra/app separation, and Git as the source of truth; you can walk through GitOps workflows clearly in a technical discussionRAG architecture depth — including vector databases (Qdrant, Pinecone, ChromaDB, or similar), embedding strategies, and retrieval optimization Docker and Kubernetes for production AI deployments Python as your primary language, with FastAPI or similar for API developmentSQL and NoSQL databases (PostgreSQL, MongoDB, Supabase, or similar) Fluent spoken and written English — you can discuss, restate, and reason through verbal technical requirements in real time without friction Skills That Will Make You Stand OutExperience with open-source LLM platforms (Ollama, vLLM, Hugging Face Inference) in production Familiarity with n8n or similar workflow automation platformsExperience with LLM observability tools (Langfuse, LangSmith, Arize, or similar) Background in telecommunications, broadband, or infrastructure-heavy industries Familiarity with ServiceNow ITOM or enterprise IT management platformsExperience with Azure DevOps or GitHub Actions for CI/CDContributions to open-source AI projects