Software Engineer (AI)

The Team + The Role

Pendo spent a decade helping companies understand how people use their software. Agents are the next surface, and this team builds the product for it: customers install Pendo on their own agentic systems, including MCP servers, agent frameworks, and copilots, and Pendo shows them what those agents are actually doing. The team helps customers understand which tools get called, where calls fail, where a contract confuses the model, and what to fix next.

As an AI Software Engineer, you will own features end to end across the service, interface, and the seam between them. You will work across Go services, Vue interfaces, install experiences, instrumentation, telemetry, and LLM-backed product capabilities. You will start with well-shaped problems and take on progressively more ambiguous work as you build context, writing code others can operate and raising issues early when a spec does not match reality.

This role is based in our New York City office.

What this looks like day-to-day

• Full-stack feature delivery: Ship full-stack features end to end across Go services and Vue interfaces. Work across backend and frontend boundaries to build reliable, usable production experiences.
• Customer install and instrumentation: Build the install and instrumentation experience customers drop into their own agentic systems.
• Agent behavior visibility: Capture agent behavior and make it legible for customers by exposing tool calls, failures, latency, and contract mismatches.
• LLM-backed product development: Work on LLM-backed features including prompt and context design, tool calling, evaluation, and failure modes.
• Safe, incremental shipping: Ship in small increments behind feature flags and test to the level of product and technical risk using tools like Jest and Cypress while accounting for non-deterministic model output.
• Production ownership: Own what you ship in production through logging, monitoring, fast resolution, and follow-up work.
• AI-enabled workflow: Use AI tools as a normal part of your development workflow with curiosity and discipline.
• Team collaboration: Give useful code reviews, write durable documentation, and provide reasonable estimates for well-scoped work.

Qualifications

Must-haves

• 3+ years of experience shipping full-stack features to production in a SaaS environment.
• Strong proficiency in at least one backend language such as Go, Java, Python, or C++, and one modern frontend framework such as Vue, React, or Angular.
• Experience designing APIs and building services on AWS or GCP against SQL databases.
• Hands-on experience building with LLMs, including API integration, prompt and context design, or tool calling (professional or substantial personal work).
• Experience with Agent frameworks (LangChain, LangGraph) and LLM evaluation tooling.
• Ability to write unit, integration, and end-to-end tests based on risk, with comfort using safe rollout patterns such as feature flags and canary releases.
• Demonstrated ability to take a well-scoped problem to production independently.
• Active use of AI tools in your development workflow.
• Strong written communication skills and a BS in Computer Science or equivalent experience.

Nice-to-haves

• Experience building or operating an MCP server or comparable agent tooling.
• Experience shipping SDKs or instrumentation libraries that customers install into their own systems.
• Experience with analytics or observability products that turn high-volume events into actionable insights.
• Vue or data visualization tools such as Highcharts or D3.