Staff Software Engineer, AI Platform

About the role

Our Agent Studio team is building the foundational platform that enables every engineering team across the company to create, deploy, and evaluate AI agents. We're looking for a Platform Engineer with a forward-deployed mindset—someone who can architect and ship robust platform capabilities, while also rolling up their sleeves alongside product teams to ensure those capabilities succeed in production. You will collaborate closely with consuming teams, understand their agent use cases firsthand, co-build tools and integrations, and translate those learnings back into a scalable, self-serve platform. This position reports to a Senior Manager, Software Engineering and is a 2 days per week hybrid role in our Austin office.

Responsibilities

• Forward Deployed / Team Enablement (50%)
  • Co-Building & Enablement: Partner directly with product teams to unblock agent use cases, co-build initial agents, and drive adoption via office hours, integration guides, and reference implementations.
  • Domain & Persona Alignment: Leverage knowledge of the built environment and ConTech platforms (Procore, Autodesk CC, Buildertrend, OpenSpace) to address key friction points for GCs, Subcontractors, Owners, PMs, and Field Engineers.
  • Platform Feedback Loop: Translate fragmented, team-specific requirements into generalized platform capabilities and concrete roadmap proposals.
  • Technology Evaluation: Collaborate with the AI Architect and engineering leads to evaluate, benchmark, and adopt emerging agent frameworks and tools.
• Platform Engineering (50%)
  • Runtime & Security Infrastructure: Design and build the agent runtime, tool registry, and execution security controls, including process isolation, egress restrictions, and credential scoping.
  • Evaluation Frameworks: Build automated testing harnesses, LLM-as-a-judge pipelines, regression tracking, and quality dashboards for agents.
  • Agent Observability: Own end-to-end tracing using OpenTelemetry, session replay, cost attribution, and latency profiling across multi-step agent runs.
  • MCP, Integrations & API Contracts: Maintain Model Context Protocol (MCP) servers, third-party tool integrations, and stable, well-versioned platform API schemas for cross-org consumption.

Requirements

• 5+ years of software engineering experience, with at least 2 years focused on developer platforms, internal tooling, or infrastructure.
• Hands-on experience building and deploying production LLM applications or agentic systems.
• Deep proficiency in Python and/or TypeScript; comfortable reading and navigating Go codebases.
• Proven track record designing and maintaining developer-facing REST or GraphQL APIs.
• Strong grasp of agent architecture: tool usage, multi-step reasoning, memory management, structured output, and error handling.
• Pragmatic "bias for action"—capable of shipping rapidly without compromising long-term platform integrity.
• Familiarity with the ConTech landscape (Procore, Autodesk Construction Cloud, Buildertrend, OpenSpace).
• Clear understanding of core customer personas in the built environment and their operational pain points.

Preferred Qualifications

• Background in ConTech support, specifically troubleshooting AI features, LLM interfaces, or automated toolsets.
• Hands-on experience with Model Context Protocol (MCP) or modern tool-calling frameworks.
• Familiarity with LLM evaluation methodologies (automated judging, red-teaming, eval-driven development).
• Experience with workflow orchestration engines (e.g., Temporal, Prefect, Airflow) for long-running agent tasks.
• Experience implementing AI/ML observability tools (e.g., OpenTelemetry, Langfuse, Datadog).
• Prior experience in forward-deployed, solutions engineering, or developer advocacy roles.

Pay

Base Pay Range: $168,560.00 - $231,770.00 USD Annual

This role may also be eligible for Equity Compensation and/or Bonus Incentive Compensation.

Schedule

2 days per week hybrid role in our Austin office.