Applied AI Engineer

Role overview

As an Applied AI Engineer, you will design, build, and ship LLM-powered agents and applications. You will partner with the Data Science team to translate strategies into reliable, production-grade systems that solve business problems.

Responsibilities

• Build and deploy LLM agent systems from prototype to production
• Collaborate with Data Science on prompt engineering and agent specifications
• Implement predictable agent behavior (within guardrails and model configurations)
• Own the full lifecycle of agent services:
  • tests, monitoring, logging, and iteration
• Integrate with APIs and work with platform/infrastructure teams to deploy and maintain services in the cloud
• Develop multi-step workflows, including tool use / function calling

Requirements

• 3+ years of software engineering experience with strong Python proficiency
• Hands-on experience building applications powered by large language models
  • Familiarity with Claude, GPT, Gemini
• Experience implementing function calling, tool use, and multi-step agent workflows
• Strong debugging and problem-solving skills for complex agent failures
• Solid understanding of RAG architectures, including embedding models and vector databases
  • e.g., Pinecone, Weaviate, pgvector, Vertex AI Vector Search
• Ability to work cross-functionally with Data Science, Product, and Engineering
• Comfort coding and integrating into API / microservices and deploying cloud services

Nice to have

• Experience with LLM evaluation frameworks (e.g., RAGAS, LangSmith, Braintrust, custom evals)
• Familiarity with agent frameworks and orchestration patterns (e.g., LangChain, LangGraph, CrewAI, Vertex AI Agent Builder)
• Experience with multi-agent routing/delegation/coordination patterns
• Familiarity with MLOps and CI/CD for ML systems
• Experience with streaming responses, async architectures, and real-time agent interactions
• Contributions to open-source AI/ML projects
• Exposure to Google Cloud Platform / Vertex AI ecosystem