SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Planet Labs is seeking an experienced Software Engineer to lead the hands-on deployment of enterprise-grade AI applications and infrastructure within the Corporate Engineering team. You will design, build, and maintain production-ready AI applications leveraging platforms like Google Gemini Enterprise Agent Platform, Cursor, and Claude. Your responsibilities include building end-to-end intelligent agent experiences, automating complex business workflows, and supporting the evaluation and integration of enterprise AI platforms.
You will maintain a centralized AI Gateway to manage LLM API routing, rate limiting, cost controls, and model selection across internal teams, and integrate an AI Agent Registry to catalogue, govern, and monitor agents company-wide. A critical aspect of this role involves implementing robust logging, monitoring, and alerting frameworks to track all AI touchpoints, managing AI data pipelines that adhere to ITAR and EAR standards, and collaborating with Security and Legal teams to institute strict data access controls and compliance checks.
You will promote industry best practices for AI engineering and evangelize AI tools and capabilities across both technical and non-technical business units to accelerate enterprise adoption and productivity. This is a full-time hybrid role requiring 3 days per week in the San Francisco office.
Required qualifications include 6+ years of software engineering experience, a Bachelor's degree in Computer Science or equivalent, hands-on experience developing and deploying applications using GCP and AWS, and experience working in regulated engineering environments (ITAR, EAR, FedRAMP). You should have expertise with Python, Vector Databases, SQL, and familiarity with AI Gateways, Agent Registries, and AI orchestration platforms. Prior experience with Gemini Enterprise App and Claude Code is a plus.
