Lead Support Engineer(L3)

mroads; Bogotá; On-site; COP 12,000,000 - 18,000,000; Full time

Job summary

Mroads is seeking Lead support engineers to be the first line of support for our AI platform in Bogota. You will triage ServiceNow tickets, assist product teams with APIs, and diagnose production issues across LLM gateways and Kubernetes services.

This role is technical, customer-facing, and requires curiosity and strong documentation skills to create SOPs and post-incident procedures. If you love complex systems and helping teams resolve issues quickly, join us.

Qualifications

• 10 years in app support, SRE, or platform engineering
• Strong API troubleshooting and incident management skills
• APM/distributed tracing experience (Dynatrace preferred)
• Python or Node.js literacy
• Basic LLM/AI platform knowledge (models, tokens, embeddings, guardrails)
• Strong communication and customer-facing skills
• Technical Documentation writing, SOPs, and other procedures as follow ups to incidents.

Responsibilities

• Lead first-line support for our AI platform and triage ServiceNow tickets.
• Help product teams use our APIs and debug production issues.
• Escalate to engineering when needed and coordinate incident response.
• Diagnose issues spanning LLM gateways, workflow engines, Kubernetes services, and data systems.

Skills

10 years in app support / SRE / platf

API troubleshooting

Incident management

Python or Node.js literacy

LLM/AI platform knowledge

Strong communication / customer-facing

Tools

Dynatrace

ServiceNow

Job description

We need Lead support engineers to be the first line of support for our AI platform. They will triage ServiceNow tickets, help product teams use our APIs, debug production issues, and elevate to engineering when needed.

This is not a traditional help desk role. Issues often span LLM gateways, workflow engines, Kubernetes services, and enterprise data systems. The right person is technical, curious, and good with customers.

Must Haves:

• 10 years in app support, SRE, or platform engineering
• Strong API troubleshooting and incident management skills
• APM/distributed tracing experience (Dynatrace preferred)
• Python or Node.js literacy
• Basic LLM/AI platform knowledge (models, tokens, embeddings, guardrails)
• Strong communication and customer-facing skills
• Technical Documentation writing, SOPs, and other procedures as follow ups to incidents.

Nice to haves:

• LiteLLM, Temporal, GraphQL, Kafka, AWS Bedrock/EKS
• AI agent or chatbot platform experience
• Harness CI/CD or enterprise SSO familiarity
• Fluent in using Cursor + MCP tools to diagnose issues and write documents