A complete application in a minute
Tailored resume and cover letter, ready to send.
LangChain is seeking a senior technical support escalation engineer to assist AI engineers and infrastructure architects, diagnosing issues across customer deployments and LangChain products. This role focuses on production triage and root-cause analysis.
You will work with APIs, SDKs, distributed systems, and cloud stacks, applying strong Python coding and observability practices. Knowledge of Kubernetes and Docker, and the ability to read logs and metrics, are essential for success.
This role is the main escalation point for technical support questions from AI engineers and infrastructure architects, diagnosing problems across customer setups, the company’s products, and deployments. A strong candidate brings several years of technical support, solutions engineering, or SRE work in demanding B2B settings, with expert troubleshooting across APIs, SDKs, distributed systems, and cloud stacks. Python programming, container tooling, and comfort reading logs, traces, and metrics round out the profile.
The work sits where AI agents meet production, so support means debugging live LLM applications and helping teams improve observability and evaluations. AI can speed up triage and drafting, but judgment about root causes, clear writing, and calm handling of critical incidents stay human. The role also shapes how support itself is done for AI platforms, which is still being defined.
A person here would gain hands on exposure to agent frameworks, observability and evaluation tooling, and the debugging patterns of production LLM systems. Building that means getting fluent with the company’s open source frameworks and platform, practicing trace and metric analysis, and learning how LLM providers and OpenTelemetry integrations behave under load.
This is our own read, written from the employer’s posting and the company’s Spotlight. The employer’s posting is the source of truth for the role.
LangChain provides an open agent engineering platform and open source frameworks for building, testing, deploying, monitoring, and governing AI agents, per the company.