AI Engineer
Kobie
full-remotemidpermanentbackenddata St. Petersburg, FL 2 days ago via LinkedIn
See how well this job matches your profile
Sign up to get an AI match score and generate a tailored application in seconds.
Get your match scoreTags
PythonLangChainLangGraphLLMRAGAmazon AgentCoreSnowflakeEvaluation FrameworksCI/CDDocker
About the role
Role Overview
Kobie is hiring a hands-on AI Engineer to build and ship features on an internal agent platform running on Amazon AgentCore. This is not a research-only role—you will prototype, deploy, monitor, and iterate on capabilities used by real teams.
What You’ll Build
- Agent harnesses in Python using LangChain/LangGraph (tool-calling, structured outputs, retries, streaming, memory)
- Agent packaging for the AgentCore Runtime with clean production-ready context, tools/skills, and subagents
- Tools/skills agents call, including:
- API integrations
- SQL queries against Snowflake
- Snowflake-backed knowledge retrieval with clear contracts and Pydantic validation
Evaluation & Reliability
- Build evaluation harnesses (e.g., golden datasets, LLM-as-judge, regression suites) using AgentCore Evaluations and integrate into CI
- Add production guardrails around tool execution:
- auth scoping
- input/output validation
- PII and prompt-injection protections
- hallucination mitigation
- Own what you ship: deploy via Amazon AgentCore, monitor traces, and fix issues when they break
Collaboration
- Partner with data engineers on Snowflake-backed retrieval patterns (Cortex Analyst / Cortex Search Services)
- Help evolve internal engineering patterns as the stack changes
Required Qualifications
- 3+ years professional Python experience with production service building/operations
- 1+ years hands-on LLM work in production (prompt/context engineering, tool/function calling, structured outputs, RAG)
- Working knowledge of LangChain/LangGraph or comparable agent frameworks (AgentCore Strands, CrewAI, Semantic Kernel)
- Experience with LLM observability (e.g., 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
- Strong written communication and good engineering judgment
Nice-to-Haves / Notes
- A bachelor’s degree is not required; equivalent practical experience is valued.
About Kobie
Kobie is a loyalty-focused technology company that helps major brands build lasting emotional connections with consumers. Based in St. Petersburg, Florida, Kobie operates a flexible, remote-friendly culture and builds internal platforms and tools to power large loyalty programs.
Scraped 6/18/2026