[Remote] AI Engineer

Note: The job is a remote job and is open to candidates in USA. Kobie is a Top Workplace in the USA focused on loyalty solutions for major brands. They are seeking a hands-on AI Engineer to build and evaluate an internal agent platform that automates workflows and enhances data insights.ResponsibilitiesBuild agent harnesses in Python using LangChain and LangGraph, including tool-calling, structured outputs (Pydantic/JSON schema), retries, streaming, and memoryPackage agent harnesses for the AgentCore Runtime with appropriate context, tools, skills, and subagents that fit cleanly into production flows and scenariosWrite the tools and skills agents use API integrations, SQL queries against Snowflake, Snowflake backed knowledge retrieval with clear contracts and Pydantic validationBuild evaluation harnesses (golden datasets, LLM-as-judge, regression suites) using AgentCore Evaluations, and wire them into CIImplement guardrails around tool execution: auth scoping, input/output validation, PII and prompt-injection protections, and hallucination mitigationYou own what you ship: prototype, deploy through Amazon AgentCore, monitor traces, and fix it when it breaksPartner with data engineers on Snowflake backed retrieval patterns (Cortex Analyst and Cortex Search Services)Contribute to refining our internal engineering patterns as the stack evolvesSkills3+ years of professional Python, with production experience building and operating services1+ years of hands-on work with LLMs in production: prompt/context engineering, tool/function calling, structured outputs, RAGWorking knowledge of LangChain/LangGraph or a comparable framework like AgentCore Strands, CrewAI, or Semantic KernelExperience with LLM observability tools: Amazon CloudWatch, LangSmith, Langfuse, MLflow, or OpenTelemetryExperience designing evaluation frameworks (MLFlow, DeepEval, LLM-as-judge, multi-turn regression)Fluency with Git, Docker, and modern API frameworksClear written communication and the judgment to know when something is ready to shipA bachelor's degree is not required. Equivalent practical experience: including bootcamps, self-taught work, career changes, or non-CS technical degrees countsHands-on experience with Amazon Bedrock and/or AgentCore as a developer: runtime, gateways, memory, policy, guardrails, observability, awscli, evaluationsExperience with Snowflake, Snowpark, or Snowflake CortexFluency in writing and reading SQL, as well as understanding semantic modelsFamiliarity with multi-agent patterns: supervisor/router, subagent/handoff, reflection, human-in-the-loopA considered view on where agents should and shouldn't act and comfort pushing back when 'let's add an agent' isn't the right answerExperience in Loyalty, MarTech, AdTech, or a comparable data rich B2B domainBenefitsFreedom to work remotelyFlexible Time Off to recharge when neededNine Company-Wide HolidaysA diverse suite of benefits prioritizing your growth, development, and personal well-beingCompany OverviewKobie is a global, market-leading, end-to-end loyalty solutions provider for the world’s most successful brands. It was founded in 1990, and is headquartered in St. Petersburg, Florida, USA, with a workforce of 201-500 employees. Its website is http://www.kobie.com/.