Data Scientist / Machine Learning Engineer (LLM & RAG Systems) - Remote

Overview

This role involves developing and optimizing RAG pipelines to enhance troubleshooting using LLMs, implementing vector embedding models, and deploying models on AWS.

In Short

• Develop and optimize RAG pipelines for LLM-driven troubleshooting.
• Work with PyVector for efficient data storage and retrieval.
• Implement vector embedding models to improve accuracy.
• Build high-quality Python code for AI applications.
• Deploy and scale models on AWS (S3, Lambda, ECS, SageMaker, Bedrock).
• Fine-tune and evaluate LLMs for specific tasks.
• Implement efficient document indexing and retrieval.
• Experiment and iterate features based on customer feedback.
• Collaborate with a skilled team in industrial AI.
• Adapt to changing priorities and take ownership of challenges.

Requirements

• Strong Python development skills with machine learning or NLP experience.
• Experience with RAG architectures and knowledge retrieval techniques.
• Familiarity with PyVector for vector search and retrieval.
• Experience using vector embedding models (e.g., OpenAI, Bedrock Titan).
• Understanding of embedding models and retrieval best practices.
• Experience with AWS for cloud-based ML deployment.
• Knowledge of LangChain, LlamaIndex, or other RAG frameworks.
• Ability to work in a fast-paced, experimental environment.
• Self-starter who can work autonomously in a remote setting.
• Strong problem-solver who thrives in challenging situations.

Benefits

• Work on cutting-edge AI in a complex industry.
• Be part of a small, agile team where your work matters.
• Enjoy full remote flexibility with autonomy to shape your role.
• Build a product that solves real-world problems for clients.