AI Engineer
Remote • St. Petersburg, Florida • Full-Time
Posted 4mo ago
Job Location
St. Petersburg, Florida
Tech Stack
Remote Work Policy
Fully remote
Employment Type
Full-Time
Categories
AI Agent Engineer
About the job
Kobie is seeking a hands-on AI Engineer to join their team and contribute to building an internal agent platform. This platform automates analyst workflows, extracts insights from program data, and provides an LLM-native interface for complex loyalty logic. The role involves building agent harnesses, developing tools for agents, and ensuring the reliability and evaluation of production features. This is a practical, shipping-focused role, not a research position, requiring individuals who can prototype, deploy, monitor, and iterate on features used by real teams. The ideal candidate is a careful reasoner, ships working code, and can independently learn new tools.
Responsibilities
- Build agent harnesses in Python using LangChain and LangGraph, incorporating features like tool-calling, structured outputs, retries, streaming, and memory.
- Package agent harnesses for the AgentCore Runtime with necessary context, tools, skills, and subagents for production flows.
- Develop tools and skills for agents, including API integrations, SQL queries against Snowflake, and knowledge retrieval with clear contracts and validation.
- Construct evaluation harnesses using AgentCore Evaluations, including golden datasets, LLM-as-judge, and regression suites, and integrate them into CI.
- Implement guardrails for tool execution, covering authentication, input/output validation, PII protection, prompt-injection prevention, and hallucination mitigation.
- Prototype, deploy through Amazon AgentCore, monitor traces, and resolve issues for shipped features.
- Collaborate with data engineers on Snowflake-backed retrieval patterns.
- Contribute to refining internal engineering patterns as the technology stack evolves.
Requirements
- 3+ years of professional Python experience, including production experience building and operating services.
- 1+ years of hands-on experience with LLMs in production, covering prompt/context engineering, tool/function calling, structured outputs, and RAG.
- Working knowledge of LangChain/LangGraph or a similar framework (AgentCore Strands, CrewAI, Semantic Kernel).
- Experience with LLM observability tools (Amazon CloudWatch, LangSmith, Langfuse, MLflow, OpenTelemetry).
- Experience designing evaluation frameworks (MLFlow, DeepEval, LLM-as-judge, multi-turn regression).
- Fluency with Git, Docker, and modern API frameworks.
- Clear written communication skills and good judgment for shipping readiness.
- Equivalent practical experience (bootcamps, self-taught, career changes, non-CS technical degrees) is accepted in lieu of a bachelor's degree.
Benefits
- Flexible Time Off
- Nine Company-Wide Holidays
- A diverse suite of benefits prioritizing growth, development, and personal well-being