Technical Services Engineer
Salary not listed • Mexico City • Full-time
Posted 1mo ago
Job Location
Mexico City
Tech Stack
Remote Work Policy
On-site
Employment Type
Full-time
Categories
AI Engineer
About the job
We are establishing a new Technical Services capability in Mexico City to support a platform that empowers customers to build, deploy, and operate AI applications using MongoDB. As an early member of this growing team, you will play a key role in shaping our customer support strategies, collaborating with Engineering and Product teams, and establishing the team's technical practices from the ground up. The platform integrates AI application workflows, orchestration, model and tool integrations, cloud infrastructure, data services, and observability. The support team will address complex issues across these layers to ensure customers can successfully operate their applications.
As a Technical Services Engineer, your primary focus will be assisting customers with building, deploying, and operating AI applications on the MongoDB platform. You will investigate and resolve issues spanning application behavior, agent workflows, APIs, cloud infrastructure, and data services. This role is ideal for an engineer who thrives on learning new technologies, enjoys direct customer interaction, and excels at applying structured troubleshooting to intricate systems. You will also contribute to the broader MongoDB Technical Services organization as customer needs evolve.
Responsibilities
- Support customers and internal stakeholders working with AI applications and agentic workflows.
- Investigate issues involving LangGraph execution, MCP and tool integrations, model-provider behavior, memory, checkpoints, streaming, retries, and timeouts.
- Read and debug Go, TypeScript, and Python services and agent implementations.
- Troubleshoot Docker and Kubernetes workloads, including deployments, containers, networking, secrets, resource failures, and deployment configuration.
- Utilize logs, metrics, traces, and application errors to form hypotheses and identify root causes.
- Troubleshoot MongoDB Atlas connectivity, authentication, TLS, network access, indexing, and vector-search issues.
- Reproduce customer problems, develop workarounds, and drive issues to resolution.
- Communicate clearly with customers during complex or high-impact incidents.
- Create knowledge articles, troubleshooting guides, diagnostic scripts, and reusable runbooks.
- Partner with Engineering, Product, Security, and other Technical Services teams on escalations and product improvements.
- Contribute to broader MongoDB database and cloud support cases as needed.
Requirements
- 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.
- Ability to read and debug Go, TypeScript, and Python services, SDKs, and agent workflows, including asynchronous execution, HTTP clients, retries, and timeouts.
- Experience with Docker and Kubernetes, including deployments, containers, networking, secrets, resource management, and deployment troubleshooting.
- Familiarity with REST/JSON APIs, streaming protocols, API keys, OAuth/JWT, RBAC, and service accounts.
- Experience using metrics, events, logs, traces, error monitoring, and alerting to diagnose production issues.
- Experience investigating issues across application, platform, and data layers, communicating clearly with customers, and driving problems through resolution.
- Experience with MongoDB, MongoDB Atlas, Atlas Vector Search, Voyage AI or another distributed database (Bonus Points).
- Experience using any cloud services stack such as AWS, Azure or GCP (Bonus Points).
- Experience with Control/Data-plane architecture services (Bonus Points).
- Experience with Terraform, GitHub Actions, CodeBuild, or other CI/CD systems (Bonus Points).
- Experience with Helm, operators, container registries, or advanced Kubernetes networking (Bonus Points).
- Broad awareness of customer workloads and use cases, including performance, availability, and scalability (Bonus Points).