Engineer, Software Engineering

Key Responsibilities

• Design and develop robust data extraction pipelines for PDFs, HTML, and semi-structured/unstructured data sources
• Implement and optimize ML/NLP models for information extraction and document understanding
• Work with Large Language Models (LLMs) for tasks like classification, summarization, and structured extraction
• Build scalable backend services using Python
• Develop and maintain APIs and microservices
• Collaborate with frontend engineers to integrate features (React-based UIs)
• Work with databases and search systems for indexing and retrieval
• Ensure high performance, reliability, and scalability of systems
• Debug and improve existing pipelines and workflows

Required Skills
Strong programming skills in Python
Experience working with data processing pipelines
Hands-on experience with NLP / ML techniques
Familiarity with LLMs and prompt engineering / fine-tuning concepts
Experience parsing or extracting data from PDFs / HTML / web sources
Knowledge of REST APIs and backend development
Experience with databases (SQL/NoSQL)

•  
• Good understanding of software engineering fundamentals (data structures, system design, testing)

Nice to Have
Experience with document AI / OCR tools
Familiarity with frameworks like FastAPI
Experience with React or frontend development
Knowledge of distributed systems / streaming pipelines

• Exposure to vector databases / embeddings / semantic search
• Experience deploying ML models to production
• Understanding of cloud platforms (AWS / GCP / Azure)

What We Offer

• Opportunity to work on cutting-edge problems involving LLMs and document intelligence
• High ownership and impact on core product systems
• Collaborative and fast-paced engineering culture
  • Flexible work environment