Job Description
Enzziro is hiring an AI Engineer to lead our "AI Army." We aren't just wrapping ChatGPT; we are building sophisticated, context-aware AI agents for our clients using LangChain and Python.
You will bridge the gap between raw LLM capabilities and real-world business applications. Your primary focus will be designing RAG (Retrieval Augmented Generation) pipelines that allow our clients to chat with their own data, automating complex workflows, and integrating these intelligent agents into our Next.js and Flutter applications.
This is a project-based role for a developer who understands the bleeding edge of AI. You will be experimenting with the latest models, optimizing token usage, and reducing latency to create seamless AI experiences.
What you’ll bring
- LangChain Mastery: You know how to build chains, agents, and custom tools within the LangChain framework.
- Python Proficiency: You write efficient Python code to handle data processing and logic.
- RAG Expertise: You understand how to chunk data, generate embeddings, and store them in vector databases (like PostgreSQL with pgvector).
- Prompt Engineering: You know how to structure prompts to get consistent, reliable JSON outputs from LLMs.
- Full Stack Awareness: You understand how to expose your AI agents via APIs (FastAPI) so our frontend teams can consume them.
Benefits
- 100% Remote: Work from anywhere on your own schedule.
- Innovation First: Work with the newest AI tools before they become mainstream.
- High-Value Projects: Build tools that solve expensive problems for businesses.
- Competitive Pay: We value specialized AI expertise highly.
- Growth: Define the AI strategy for a rapidly growing tech agency.