AI Engineer

Join a National Top Workplace

Named a Top Workplace in the USA and Top Remote Workplace, Kobie is where the best minds in loyalty come together, driven by passion and innovation. We’re always looking for talented individuals who are ready to join a collaborative, growth-focused culture. As a partner to some of the world’s most recognized brands, we are leaders in loyalty, helping brands build lasting emotional connections with their consumers.

While our headquarters are nestled in sunny St. Petersburg, Florida, Kobie embraces a flexible work environment, offering teammates the freedom to work remotely. We understand the importance of work-life balance and support our team with:

• Flexible Time Off to recharge when needed
• Nine Company-Wide Holidays
• A diverse suite of benefits prioritizing your growth, development, and personal well-being

Discover more about our perks and benefits here.

Kobie is a values-led organization where we believe that everyone is a leader, regardless of their position or role.

Kobie runs some of the largest loyalty programs in the world. We're building an internal agent platform on Amazon Agent Core that automates analyst workflows, surfaces insights from program data in Snowflake, and gives our teams and clients an LLM-native way to work with complex loyalty logic.

We're looking for a hands‑on AI Engineer to ship on that platform: building agent harnesses, writing the tools those agents call, and owning the reliability and evaluation of what goes to production. This is not a research role. You'll prototype, ship, monitor, and iterate on features used by real teams.

Our team tends to be people who reason carefully, ship working code, and pick up new tools without a lot of hand holding. There’s no single path into this role. We value the impact of what you’ve built and your track record of building things that hold up.

• Build agent harnesses in Python using Lang Chain and Lang Graph, including tool‑calling, structured outputs (Pydantic/JSON schema), retries, streaming, and memory
• Package agent harnesses for the Agent Core Runtime with appropriate context, tools, skills, and subagents that fit cleanly into production flows and scenarios
• Write the tools and skills agents use API integrations, SQL queries against Snowflake, Snowflake backed knowledge retrieval with clear contracts and Pydantic validation

• Build evaluation harnesses (golden datasets, LLM‑as‑judge, regression suites) using Agent Core Evaluations, and wire them into CI
• Implement guardrails around tool execution: auth scoping, input/output validation, PII and prompt‑injection protections, and hallucination mitigation
• You own what you ship: prototype, deploy through Amazon Agent Core, monitor traces, and fix it when it breaks

• Partner with data engineers on Snowflake backed retrieval patterns (Cortex Analyst and Cortex Search Services)
• Contribute to refining our internal engineering patterns as the stack evolves

• 3+ years of professional Python, with production experience building and operating services
• 1+ years of hands‑on work with LLMs in production: prompt/context engineering, tool/function calling, structured outputs, RAG
• Working knowledge of Lang Chain/Lang Graph or a comparable framework like Agent Core Strands, CrewAI, or Semantic Kernel
• Experience with LLM observability tools:
  Amazon Cloud Watch, Lang Smith, Langfuse, MLflow, or Open Telemetry
• Experience designing evaluation frameworks (MLFlow, Deep Eval, LLM‑as‑judge, multi‑turn regression)
• Fluency with Git, Docker, and modern API frameworks
• Clear written communication and the judgment to know when something is ready to ship

• Hands‑on experience with Amazon Bedrock and/or Agent Core as a developer: runtime, gateways, memory, policy, guardrails, observability, awscli, evaluations
• Experience with Snowflake, Snowpark, or…