AI/ML Engineer — MCP Infrastructure

Role overview Build and operate the infrastructure that supports production AI agents and their tools. You’ll take ownership of deployments, delivery pipelines, observability, and service reliability as the system grows, working closely with a small engineering team and its technical lead.

Responsibilities - Maintain and improve agent infrastructure built with LangChain, LangSmith, and/or LangGraph. - Deploy containerized services and keep them stable across environments. - Build and operate CI/CD pipelines for agent and model releases. - Set up tracing, alerts, and performance dashboards for LLM systems. - Help integrate MCP servers as new components are delivered. - Find and address latency, cost, and reliability issues before they cause incidents.

Requirements - Practical DevOps experience owning production deployments and operations. - Experience with Docker and a container orchestration platform such as ECS or Fargate. - Experience with GitHub Actions and AWS services such as ECS, RDS, S3, and CloudWatch. - Production experience with LangChain, LangSmith, or LangGraph, plus familiarity with the MCP protocol. - Understanding of LLM production concerns, including token costs, latency, rate limits, and monitoring. - Ability to work independently in a small team and communicate fluently in English in daily asynchronous work.

Nice to have - Experience configuring LangSmith tracing and evaluations. - Familiarity with observability tools such as Datadog or Grafana. - Experience working directly with a senior client-side engineer.

Benefits and work setup - Remote contract open to candidates in Latin America, with a six-month initial term and potential extension. - Compensation of $4,000–$5,000 USD per month, paid bi-weekly. - Monday–Friday schedule aligned with US Eastern Time, 9 a.m.–6 p.m. - Paid time off accrual begins after a three-month trial period.