Unstructured.io Developer-3

Job Type: Contract

Job Category: IT

Job Description

Develop and enhance data processing pipelines using Unstructured.io for converting unstructured data (PDF, DOCX, HTML, Emails, Scans) into structured formats.
Integrate extracted data with Vector Databases or Search Indexing workflows for LLM/RAG applications.
Optimize parsing performance, accuracy, and consistency across various document formats.
Work with Python-based microservices, APIs, and orchestration frameworks.
Collaborate with Data Engineering, ML, and Product teams to design scalable ingestion architectures.
Implement best practices for scalable, reusable pipeline components.
Monitor, debug, and resolve pipeline issues across staging and production environments.

Overall IT Experience: 8+ Years
3+ years hands-on experience implementing Unstructured.io in production environments.
Strong experience with Python, including parsing, data transformation, and API development.
Experience building RAG (Retrieval-Augmented Generation) or Document AI workflows.
Hands-on with Vector Databases (Pinecone, Weaviate, Chroma, FAISS, Milvus, etc.).
Familiarity with Cloud Platforms (AWS preferred).
Experience with Docker, Git, CI/CD pipelines.

Experience with frameworks like LangChain / LlamaIndex.
Knowledge of NLP, embeddings, and tokenization.
Experience integrating with LLM providers (OpenAI, Anthropic, Azure OpenAI, etc.).
Familiarity with document OCR tools (Tesseract, Azure Form Recognizer, AWS Textract).

Required Skills

CLOUD DEVELOPER

SQL APPLICATION DEVELOPER