Be the go-to escalation point for technical support inquiries—diagnosing issues across customer setup, LangChain products, and deployment issues.
Work directly with engineering, operations, documentation, and product teams to resolve bugs, suggest patches, and advocate for customer needs.
Partner with Deployed Engineering to support critical enterprise customers.
Build and refine internal tooling, diagnostics, and runbooks for complex issue triage.
Lead post-mortems for critical incidents and feed learnings back into product and documentation.
Help refine KPIs for support health (MTTR, CSAT, bug recurrence) and drive continuous improvement.
Improve documentation and knowledge articles to improve 1-to-many resources and provide proactive support.
Mentor and coach other support engineers.
Requirements
4+ years in technical support, solutions engineering, or SRE roles in deeply technical B2B environments (e.g., observability, infrastructure, data platforms)
Expert troubleshooting skills across APIs, SDKs, distributed systems, and cloud-native stacks
Programming experience with Python. Bonus if you have TypeScript experience
Hands-on knowledge of Kubernetes and Docker
Comfort working with logs, traces, metrics in Datadog, and 3rd-party integrations (e.g., OpenTelemetry, LLM providers)
Experience supporting enterprise customers and collaborating with engineering on complex escalations
A bias for clarity and continuous improvement: you write succinct, helpful, and accurate responses and build a foundation for case deflection
High ownership — want to do what’s best for the customer and the company and are relentlessly results oriented