Title: AI Agent Engineer Backend Focus
Location: Palo Alto, CA
Duration: 3 Months
Only W2 candidates are eligible for this position. Third party or C2C candidates will not be considered.
Description
Role Summary
We are looking for an experienced AI Agent Engineer with strong backend software engineering skills and hands-on experience building and deploying production-grade AI agents and agent-powered applications.
The ideal candidate should have a strong builder mindset, capable of understanding complex business workflows, translating them into agentic solutions, and owning the development of reliable, scalable production systems.
The primary focus of this role is building AI agents and multi-agent workflows using code, LLM APIs, and agent frameworks, rather than traditional software engineering alone. Candidates should be comfortable working through ambiguity, defining solutions, and taking ownership from discovery through deployment and continuous improvement.
What You'll Do
- Work alongside Product Managers and domain experts to understand business workflows, identify problems, define requirements, and establish success criteria for agentic solutions.
- Design, build, test, and deploy production-grade AI agents, automations, and internal tools using LLM APIs, coding agents, and agent frameworks.
- Build multi-agent workflows that automate complex business processes, enabling agents to make decisions, execute tasks, and coordinate through defined workflows and handoffs.
- Develop reliable agent orchestration, including tool integrations, context management, state management, retries, caching, and failure handling.
- Build and maintain backend services, APIs, integrations, and data models to support agent-powered applications.
- Integrate AI agents with internal platforms, business systems, and external tools through APIs and other integrations.
- Implement evaluation frameworks, guardrails, quality checks, and human-in-the-loop approvals to ensure reliability and accuracy.
- Follow strong software engineering practices, including version control, code reviews, automated testing, CI/CD, monitoring, and staged deployments.
- Monitor production agent performance, identify areas for improvement, and continuously optimize agent workflows based on measurable outcomes.
Experience You'll Need (Must-Haves)
- Around 7+ years of professional software engineering experience, particularly in backend development and production systems.
- Around 2+ years of hands-on experience building AI agents and agent-powered production applications using code.
- Strong experience with LLM APIs, agent frameworks, and multi-agent orchestration.
- Proven experience designing, developing, and deploying production-grade backend services, REST APIs, integrations, and data models.
- Experience building reliable AI agent workflows with tool calling, context and state management, error handling, and evaluation mechanisms.
- Strong understanding of system design, algorithms, data structures, access control, and scalable application architecture.
- Experience taking ownership of solutions end to end, from understanding requirements and designing workflows to implementation, deployment, and production support.
- Ability to work through ambiguity, communicate proactively, clarify requirements, and collaborate with stakeholders.
- A strong builder mindset with the ability to measure outcomes such as time saved, errors reduced, and process efficiency improved.
Software Engineering Skills
- Strong backend development experience using Python.
- Experience building REST APIs using FastAPI or Flask.
- Strong understanding of system design, API design, data modeling, and scalable architectures.
- Experience with relational databases such as PostgreSQL, MySQL, or SQL Server.
- Understanding of schema design, joins, indexing, and query optimization.
- Experience with Git, code reviews, automated testing, CI/CD, and production monitoring.
- Ability to translate ambiguous requirements into clear technical designs and implementation plans.
AI Agent Engineering Skills
- Hands-on experience building AI agents using LLM APIs, SDKs, and agent frameworks.
- Experience designing and implementing multi-agent orchestration and agent workflows.
- Strong understanding of tool calling, context management, state management, and agent execution.
- Experience integrating agents with APIs, business systems, and external tools.
- Ability to implement evaluation frameworks, guardrails, retries, failure handling, and human-in-the-loop workflows.
- Experience deploying and maintaining AI agents in production environments with real users and measurable outcomes.
- Ability to determine when to use AI agents versus simpler automation approaches.
Good-to-Have Skills
- Frontend development experience with JavaScript (ES6+) and React.
- Experience with Claude Code or other AI-assisted development tools.
- Experience with agent frameworks such as Google ADK and LangGraph.
- Experience with Electron-based desktop applications.
- Knowledge of API documentation using Swagger/OpenAPI.
- Basic DevOps knowledge, including Docker and CI/CD.
- Experience with unit and integration testing.
Behavioral Expectations (Non-Negotiable)
- Expectation What it looks like in practice.
- Proactive communication Shares updates without being asked and flags blockers early.
- Asks the right questions Clarifies requirements upfront before starting implementation.
- Collaboration Works openly with stakeholders and seeks feedback regularly.
- Ownership mindset Takes responsibility for solutions end to end rather than simply completing assigned tasks.
- Transparency Communicates openly when something is unclear instead of making assumptions.
What Success Looks Like
- Building and deploying production-grade AI agents and multi-agent workflows.
- Delivering reliable agent-powered solutions that automate real business processes.
- Strong backend architecture and integrations supporting AI-powered applications.
- Minimal hand-holding, proactive communication, and end-to-end ownership.
- Measurable improvements in business efficiency, reduced manual effort, and fewer errors.
