Sr. Full Stack Software Engineer – AI Agents

Ontrac Solutions

About The Position

We are seeking a senior full stack software engineer for a contractor program supporting a customer engagement that builds applications around multi-agent systems developed with Google's Agent Development Kit (ADK) on Google Cloud Platform. The engineer will build complete applications, including agents, backend services and APIs, and web interfaces. The role calls for experience building ADK agents, deploying them to production on GCP, and operating them afterward, including maintaining evaluation and feedback loops that help keep agent behavior reliable. The engineer will use AI coding tools, including multiple agents running concurrently, as part of daily engineering practice. They will work closely with a technical lead, other engineers, and customer stakeholders from initial definition through final delivery. The work includes designing and implementing multi-agent architecture, building frontend and backend components, deploying and operating services on GCP, testing and evaluating agent behavior, and documenting architecture and operating procedures.

Requirements

Professional full stack software engineering experience, including production delivery on Google Cloud Platform.
Hands-on experience building and deploying AI agents with Google's Agent Development Kit (ADK).
Bachelor's degree in Computer Science or equivalent practical experience.
ADK agent development, including agent definitions, tool design, and session and state management.
Design and implementation of multi-agent systems, including delegation, sequential, parallel, and loop workflows, and clear boundaries for agent context and responsibility.
Experience building agent-quality feedback loops using evaluation sets, automated output scoring, tracing, and results to revise prompts, tools, and agent structure.
Frontend development with TypeScript and a modern component framework, including integration with agent and REST APIs, streaming responses, and authenticated sessions.
Backend service and API development, including relational database design such as PostgreSQL and versioned schema migrations.
Authentication and authorization for web applications and agent tool calls using OAuth 2.0/OIDC and JWT.
Deployment and operation of agents and application services on GCP using Cloud Run and Agent Engine.
Experience with Gemini models on Vertex AI, including prompt design, function calling, and structured output.
Agent tool integration over MCP and REST APIs.
Daily use of Claude and other AI coding assistants for design, implementation, testing, and review, including running multiple agents concurrently and verifying and correcting generated output.
Automated testing and CI/CD across the stack, including frontend and end-to-end tests and regression evaluation of agent behavior.

Nice To Haves

Experience with the Agent-to-Agent (A2A) protocol.
Retrieval and grounding experience with Vertex AI Search or vector search.
Observability experience with Cloud Trace, Cloud Logging, and OpenTelemetry.
Experience with Pub/Sub, Memorystore, and BigQuery.
Experience integrating agents with Gemini Enterprise.
Google Cloud Professional certifications.

Responsibilities

Design the multi-agent architecture, including agent roles, delegation, tool boundaries, and state handling.
Implement ADK agents and tools, including integrations with customer and third-party systems over REST and MCP.
Build the web frontend and backend services that expose agents to users, including user workflows and supporting APIs.
Deploy agents and application services to GCP on Cloud Run and Agent Engine, with CI/CD and managed environments and releases.
Build and maintain evaluation suites and feedback loops to measure agent output, surface regressions, and inform changes to prompts, tools, and agent structure.
Instrument agents and services with tracing and logging so production behavior can be inspected and debugged.
Use Claude and multi-agent workflows to accelerate design, implementation, test generation, and code review while remaining accountable for delivered code.
Deliver unit, integration, end-to-end, and agent evaluation test coverage.
Participate in code reviews.
Document architecture and operating procedures for the team and customer.
Collaborate with the technical lead, engineers, and customer stakeholders from initial definition through final delivery.