Description

You will productionize Large Language Model (LLM) solutions, transforming data science experiments into scalable, maintainable systems.

This role is remote.

Responsibilities

• Productionize open-source LLMs, including fine-tuning on custom data and implementing retrieval from vector databases.
• Design and develop RESTful APIs that interface with LLMs for user consumption.
• Modularize machine learning code to ensure system scalability and maintainability.
• Integrate APIs with MongoDB, Redis, vector databases, and embedding models.
• Write Helm charts, web front ends, and technical documentation for development plans.

Required Skills

• 5+ years of experience in software engineering or related fields.
• Advanced Python programming for back-end ML operations development.
• Expertise with Flask and FastAPI.
• Experience with OpenAPI specifications, Swagger CodeGen, Editor, and Inspector.
• Hands-on work with LLMs (Llama 2 or Mistral) and Prompt Engineering.
• Ability to productionize Hugging Face models for custom datasets.
• Proficiency with Docker and Kubernetes for managing containerized applications.
• Experience using Jupyter notebooks.
• Knowledge of MongoDB.

Preferred Skills

• Experience with Angular and Node.js.
• Familiarity with Redis and vector databases.

Key Skills

Education

Any Graduate