JD

Candidate would operate business-critical solutions on our agentic platform, including autonomous AI agents running in a serverless environment on Google Cloud. The role emphasizes quality, reliability, and high availability, and requires someone who can work independently, partner closely with stakeholders, and translate business objectives into resilient technical solutions.

Please note: our platform is serverless-first and is not primarily a Kubernetes environment. Candidates whose experience is centered on cluster management and container orchestration may not be the right fit.

•         Python, Langfuse, LangChain, and Google's Agent Development Kit (ADK)

•         Google Cloud Run for serverless compute

•         AlloyDB for PostgreSQL

•         Memorystore (Redis)

•         Design, build, and deploy complex autonomous agents in Python using LangChain and Google's Agent Development Kit (ADK)

•         Apply agentic development workflows, using test- and quality-driven practices to deliver reliable, maintainable software

•         Build and operate agents and services in a serverless architecture on Cloud Run, with attention to scalability, cost, and fault tolerance

•         Design and optimize data access using AlloyDB and Memorystore (Redis), including caching and state-management strategies suited to stateless services

•         Translate business goals and requirements into scalable, high-availability technical architectures

•         Develop and maintain business-critical systems on Google Cloud infrastructure and/or as stateless web applications

•         Establish and uphold engineering standards for testing, code quality, observability, and operational readiness

•         Collaborate with product, engineering, and business stakeholders to clarify requirements, assess trade-offs, and deliver on commitments

•         Document designs, decisions, and operational procedures to support knowledge transfer within the team

•         10+ years of professional software engineering experience delivering business-critical solutions

•         Strong Python proficiency, with production experience using LangChain

•         Hands-on experience building and deploying complex autonomous agents in production

•         Proven expertise in agentic development workflows, with a strong emphasis on test-driven and quality-focused engineering practices

•         Demonstrated depth in at least one of the following:

◦          Google Cloud infrastructure: designing, deploying, and operating production workloads on Google Cloud Platform, ideally using serverless services such as Cloud Run

◦          Full-stack engineering: extensive experience building stateless web applications

•         Experience designing and operating serverless workloads

•         Track record of translating business needs into high-availability technical solutions

•         Strong written and verbal communication skills, with the ability to explain technical concepts to non-technical audiences

•         Experience with Google's Agent Development Kit (ADK)

•         Experience with AlloyDB or PostgreSQL, and Redis / Memorystore

•         Experience with CI/CD, infrastructure as code, or observability tooling