Description
You will build and optimize language models and data extraction pipelines.
Responsibilities
- Develop and implement RAG architectures using LlamaIndex and LangChain.
- Fine-tune LLMs to improve performance on specific NLP tasks.
- Build text summarization and extraction workflows.
- Engineer features and manage vector search implementation using FAISS.
- Develop parsing logic for OCR, layout models, PDFs, and various text file formats.
Required Skills
- 5+ years of experience in Machine Learning and NLP.
- Hands-on experience with LLMs, RAG, and fine-tuning.
- Proficiency with LangChain, LlamaIndex, and LangSmith.
- Experience with Vector Databases and Vector Search.
- Practical knowledge of FAISS and embeddings.
- Experience with OCR and layout models for PDF and text parsing.
- Ability to integrate models via REST APIs.
- Strong background in Feature Engineering.
- Any Graduate degree.