Description
We are building a new Technical Services capability in Mexico to support a platform that helps customers build, deploy, and operate AI applications using MongoDB.
As a Technical Services Engineer, you will help customers build, deploy, and operate AI applications on a new MongoDB platform. You will investigate issues across application behavior, agent workflows, APIs, cloud infrastructure, and data services, while contributing to the broader MongoDB Technical Services organization as customer needs evolve.
Responsibilities:
- Supporting customers and internal stakeholders working with AI applications and agentic workflows
- Investigating issues involving LangGraph execution, MCP and tool integrations, model-provider behavior, memory, checkpoints, streaming, retries, and timeouts
- Reading and debugging Go, Typescript and Python services and agent implementations
- Troubleshooting Docker and Kubernetes workloads, including deployments, containers, networking, secrets, resource failures, and deployment configuration
- Using logs, metrics, traces, and application errors to form hypotheses and identify root causes
- Troubleshooting MongoDB Atlas connectivity, authentication, TLS, network access, indexing, and vector-search issues
- Reproducing customer problems, developing workarounds, and driving issues through resolution
- Communicating clearly with customers during complex or high-impact incidents
- Creating knowledge articles, troubleshooting guides, diagnostic scripts, and reusable runbooks
- Partnering with Engineering, Product, Security, and other Technical Services teams on escalations and product improvements
- Contributing to the broader MongoDB database and cloud support cases when needed
Requirements:
- AI and agent platforms: Hands-on experience building or troubleshooting agentic AI applications, including LangGraph, A2A, MCP, tool calling, model-provider integrations, memory, checkpoints, streaming, and human-in-the-loop workflows
- Programming and systems troubleshooting: Ability to read and debug Go, TypeScript, and Python services, SDKs, and agent workflows, including asynchronous execution, HTTP clients, retries, and timeouts
- Cloud-native platforms: Experience with Docker and Kubernetes, including deployments, containers, networking, secrets, resource management, and deployment troubleshooting
- API, identity, and security: Familiarity with REST/JSON APIs, streaming protocols, API keys, OAuth/JWT, RBAC, and service accounts
- Observability and incident response: Experience using metrics, events, logs, traces, error monitoring, and alerting to diagnose production issues
- Distributed-systems troubleshooting: Experience investigating issues across application, platform, and data layers, communicating clearly with customers, and driving problems through resolution
Nice to have:
- Experience with MongoDB, MongoDB Atlas, Atlas Vector Search, Voyage AI or another distributed database
- Experience using any cloud services stack such as AWS, Azure or GCP
- Experience with Control/Data-plane architecture services
- Experience with Terraform, GitHub Actions, CodeBuild, or other CI/CD systems
- Experience with Helm, operators, container registries, or advanced Kubernetes networking
- Broad awareness of customer workloads and use cases, including performance, availability, and scalability