Senior Software Engineer, AI Platform

As a Senior AI Fullstack Engineer , you’ll work on the core systems behind the Intent Platform, building reusable platform capabilities that engineering teams use to develop and operate AI applications and Agents. The role spans Agentic AI, backend services, APIs, data, and frontend experiences, with a focus on turning emerging AI patterns into reliable, scalable capabilities that work across different teams and use cases.

The work includes designing capabilities for agent orchestration, tool execution, RAG and retrieval, context and memory management, multi-agent workflows, model routing, evaluation, and observability.

Our current technology stack includes Google ADK, Vertex AI, LiteLLM, Python/FastAPI, PostgreSQL, and React . We are not looking for experience with this exact stack. Experience building similar systems using other agent frameworks, model platforms, orchestration layers, or modern full-stack technologies is equally relevant.

The engineer will also work on problems that come with moving AI applications from experimentation into production, including reliability, performance, scale, evaluation, security, and governance. Because developers are the primary users of the platform, the role also involves working directly with engineering teams to improve APIs, tooling, workflows, and UI/UX based on how the platform is used in practice.

We are looking for someone who has built real AI applications or Agents, understands the engineering trade-offs involved in running them in production, and can work across the stack when needed. Experience building platforms, frameworks, SDKs, or developer tools is particularly relevant, but not required.

- 4+ years of software engineering experience, with strong full-stack fundamentals across frontend, backend, APIs, and data.
- Hands-on experience building and operating AI applications or Agents in production environments.
- Experience with Agent orchestration frameworks such as Google ADK, LangGraph, CrewAI, PydanticAI , or similar technologies.
- Strong understanding of modern LLM application patterns including RAG, tool calling, context and memory management, structured outputs, and multi-agent workflows .
- Experience building backend services and APIs using technologies such as Python, FastAPI , or comparable modern frameworks.
- Experience building modern web applications using React or similar frontend frameworks, with good UI/UX intuition.
- Experience working with relational databases such as PostgreSQL and designing data models for production applications.
- Familiarity with AI platforms and foundation model ecosystems such as Vertex AI, Azure AI Foundry, Amazon Bedrock, OpenAI, or Anthropic .
- Experience with model orchestration or routing layers such as LiteLLM, OpenRouter , or similar approaches is a plus.
- Experience with AI evaluation, observability, enterprise governance, security, or responsible AI is a plus.
- Experience building platforms, SDKs, reusable frameworks, or developer tooling is highly desirable.

Exceptional candidates with fewer than 4 years of experience may also be considered if they demonstrate strong hands-on experience building and shipping AI products or Agentic systems.