Developing an AI-driven platform that enhances the accessibility and analysis of structured and unstructured data
Requirements
- Hands-on experience with AWS Bedrock for LLM fine-tuning, RAG, and generative AI applications
- Proficiency in AWS SageMaker Unified Studio for managing the full ML model lifecycle
- Experience using AWS Comprehend for NLP model development
- Proficient in Python and SQL, with strong knowledge of data preprocessing and ML model tuning
- Experience implementing vector databases, embeddings, and search pipelines for RAG architectures
- Experience with AWS Neptune for graph-based ML to improve knowledge retrieval in LLMs
- Familiarity with AWS Elasticsearch for AI-driven search solutions
Responsibilities
- Develop, train, and fine-tune LLMs and ML models using AWS Bedrock, SageMaker Unified Studio, and Comprehend
- Design and implement Retrieval-Augmented Generation (RAG) pipelines to improve LLM responses
- Use SageMaker Unified Studio to manage the end-to-end ML lifecycle, including data preparation, training, tuning, and deployment
- Build, deploy, and optimize NLP models for text classification, sentiment analysis, and entity recognition
- Implement automated ML training pipelines, leveraging MLOps best practices in AWS
- Utilize AWS Neptune for knowledge graphs to enhance LLM retrieval efficiency
- Monitor, validate, and retrain models to ensure high performance in production environments
Other
- A Bachelor’s or Master’s degree in Computer Science, Data Science, Engineering, Mathematics, or a related technical field
- 5+ years of experience in machine learning, LLM deployment, NLP, or AI-driven automation
- Ability to work in an Agile environment and adapt to rapid changes in project requirements
- Authorized to work in the US
- Subject to a complete background check
