This is a remote position.
We re looking for a systems-minded AI Engineer to lead the development of intelligent internal tools and agents at My Amazon Guy. This role is focused on building production-grade AI automations that improve our team s efficiency from SOP lookups to task automation and internal communications. If you re experienced with LLMs APIs and building real-world AI workflows this role is for you.
Key Responsibilities:
- Design and build scalable production-ready AI Agents that integrate seamlessly into My Amazon Guy s internal workflows
- Leverage OpenAI s GPT-4 and Assistants API to create intelligent agents capable of executing tasks retrieving information and interacting with users in real time
- Develop Retrieval-Augmented Generation (RAG) pipelines that pull knowledge from internal SOPs (stored in BookStack) and client data embedding them into vector databases like Chroma or Pinecone for fast and relevant retrieval
- Automate critical business actions through smart multi-step workflows that interface with the Slack API (for team messages and DMs) Asana API (for task creation and tracking) and Gmail API (for email generation and updates)
- Create REST APIs that allow internal platforms (such as MAG Source) to access AI agent capabilities like SOP lookups automated task generation and agent status reporting
- Work closely with our backend (.NET) and frontend (Angular) developers to embed agents directly into our internal tools enabling real-time productivity support
- Translate SOPs and structured data from Markdown or HTML into usable formats for AI agents via a custom ingestion pipeline
- Implement and document function-calling logic for multi-step behaviors (e.g. retrieve SOP create task send Slack message)
- Build modular testable AI systems that are auditable reliable and repeatable ensuring transparency and control in agent decision-making
- Regularly monitor agent performance identify inefficiencies and iterate quickly to optimize responses and workflows
- Stay ahead of AI trends and bring innovative ideas to future internal tools including possible expansions into SOP enforcement ChatOps or autonomous scheduling
Requirements
- At least 2 years of experience in AI engineering or backend LLM development
- Strong proficiency in Python (FastAPI Flask or similar frameworks)
- Hands-on experience with LangChain or OpenAI Function Calling / Assistants API
- Proven track record of deploying production-grade AI agents or workflows
- Familiarity with vector databases such as Chroma Pinecone or Weaviate
- Comfortable working with APIs and webhooks (Slack Asana Gmail etc.)
- Understanding of RAG pipelines and methods for reducing hallucinations
- Ability to think in systems: scalable repeatable and testable architecture
- Excellent communication and documentation skills
- Experience working remotely and cross-functionally with product engineering and operations teams
Technical Requirements:
- A dual-monitor setup is required (at least 8GB of RAM)
- Must have at least 25 MBPS internet speed
Benefits
- 40 hours a week 8 hours a day
- Competitive salary base
- Permanent WFH setup
- Unlimited FREE access to MAG School courses and SOP Library!
- Work schedule is in EST (Monday-Friday only)
- Opportunities for professional development and career advancement
You may follow up on your application by emailing us at
.
At least 2 years of experience in AI engineering or backend LLM development Strong proficiency in Python (FastAPI, Flask, or similar frameworks) Hands-on experience with LangChain or OpenAI Function Calling / Assistants API Proven track record of deploying production-grade AI agents or workflows Familiarity with vector databases such as Chroma, Pinecone, or Weaviate Comfortable working with APIs and webhooks (Slack, Asana, Gmail, etc.) Understanding of RAG pipelines and methods for reducing hallucinations Ability to think in systems: scalable, repeatable, and testable architecture Excellent communication and documentation skills Experience working remotely and cross-functionally with product, engineering, and operations teams Technical Requirements: A dual-monitor setup is required (at least 8GB of RAM) Must have at least 25 MBPS internet speed