Remote AI Engineer: Build Production Agent Platforms

Kobie; Raleigh (NC); Remote; USD 120,000 - 180,000; Full time

Benefits offered by this job

Flexible Time Off

Nine Company-Wide Holidays

Diverse benefits prioritizing growth

Job summary

Kobie seeks an AI Engineer to build and maintain an internal agent platform. You will develop agent harnesses, implement tool integrations, and ensure reliability for production teams working with loyalty data.

You will collaborate with data engineers, design evaluation harnesses, and help shape the evolution of our AI stack in a remote-first environment that values practical results and growth.

Qualifications

• 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 LangChain/LangGraph or comparable framework like AgentCore Strands, CrewAI, or Semantic Kernel
• Experience with LLM observability tools: Amazon CloudWatch, LangSmith, Langfuse, MLflow, or OpenTelemetry
• Experience designing evaluation frameworks (MLFlow, DeepEval, 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
• A bachelor's degree is not required. Equivalent practical experience: bootcamps, self-taught work, career changes, or non-CS degrees counts.

Responsibilities

• Build agent harnesses in Python using LangChain and LangGraph, including tool-calling, structured outputs (Pydantic/JSON schema), retries, streaming, and memory
• Package agent harnesses for the AgentCore Runtime with appropriate context, tools, skills, and subagents that fit production flows
• 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 AgentCore Evaluations and CI
• Implement guardrails around tool execution: auth scoping, input/output validation, PII and prompt-injection protections, hallucination mitigation
• Own what you ship: prototype, deploy through Amazon AgentCore, monitor traces, and fix it when it breaks
• Partner with data engineers on Snowflake-backed retrieval patterns
• Contribute to refining internal engineering patterns as the stack evolves

Skills

Python

LLMs in production

LangChain

LangGraph

AgentCore

SQL

Git

Docker

Tools

Snowflake

Amazon Bedrock

AgentCore

Job description

Kobie seeks an AI Engineer to build and maintain an internal agent platform. You will develop agent harnesses, implement tool integrations, and ensure reliability for production teams working with loyalty data.

You will collaborate with data engineers, design evaluation harnesses, and help shape the evolution of our AI stack in a remote-first environment that values practical results and growth.