AI/ML Engineer – MCP Infrastructure

About the role

We are building a Model Context Protocol (MCP) infrastructure for a fast‑moving mid‑market US software company. As an AI/ML Engineer you will own the health, observability, and scalability of the agentic AI platform, handling deployments, pipelines, and production stability.

Key responsibilities

• Monitor, maintain, and optimise the LangChain / LangSmith / LangGraph based agentic infrastructure.
• Manage container‑based deployments (Docker, ECS/Fargate) and ensure stability across environments.
• Design, build and own CI/CD pipelines for model and agent deployments using GitHub Actions.
• Set up and maintain observability – tracing, alerting and performance dashboards for LLM‑based systems.
• Support MCP server integration as new components are shipped by the client‑side team.
• Identify and resolve latency, cost and reliability issues before they become production incidents.
• Collaborate directly with the client’s MCP technical lead in a small, autonomous team.

Required profile

• Strong DevOps fundamentals with end‑to‑end ownership of deployments.
• Hands‑on production experience with LangChain, LangSmith and/or LangGraph.
• Deep understanding of LLM infrastructure considerations such as token cost, latency, rate limits and monitoring.
• Ability to work autonomously in a small team without daily hand‑holding.
• Near‑native English for daily async communication with US‑based stakeholders.

Required skills

• Docker and container orchestration (ECS/Fargate or equivalent).
• GitHub Actions for CI/CD pipelines.
• AWS services: ECS, RDS, S3, CloudWatch.
• Model Context Protocol (MCP) familiarity.
• LangChain, LangSmith, LangGraph.
• Observability tooling (Datadog, Grafana or similar).