Job Description
We are seeking an AI Engineer to design and implement intelligent document processing workflows that integrate OCR, Layout-aware models, and Large Language Models (LLMs). The ideal candidate will have hands‑on experience with Retrieval‑Augmented Generation (RAG), vector databases, and cloud‑based AI services, particularly in AWS.
Responsibilities
- Develop document classification and data extraction pipelines using LayoutLM and OCR technologies
- Design and implement LLM‑powered APIs for document understanding, validation, and enrichment
- Integrate Retrieval‑Augmented Generation (RAG) using vector databases (e.g., FAISS, Pinecone)
- Build and deploy scalable microservices in Python and Java
- Utilize AWS services (e.g., Textract, Lambda, S3, SageMaker) to support AI workflows
- Containerize applications using Docker and contribute to CI/CD pipelines
- Collaborate with backend and DevOps teams to integrate solutions into production systems
Required Skills
- Proficiency in Python and Java
- Hands‑on experience with LLMs (e.g., GPT, Claude) and Layout‑aware models (e.g., LayoutLM)
- Familiarity with OCR technologies (Amazon Textract, Tesseract, etc.)
- Experience with RAG pipelines and vector databases
- Strong knowledge of REST APIs and integration patterns
- Working experience with AWS cloud services
- Comfortable with containerization (Docker) and DevOps practice