AI Software Engineer ( Document Intelligence & Full Stack )

AI Software Engineer Document Intelligence & Full Stack

We are looking for an exceptional AI Software Engineer who can help us build the core technology behind these systems.

This is a hands-on role for a strong engineer who can work across AI, backend, document processing, and full-stack development. We're looking for someone who doesn't just experiment with AI, but can turn AI capabilities into reliable, production-grade software.

The Role

You will design and build systems that can ingest, understand, extract information from, and reason over large volumes of documents and unstructured data. You will work across the entire technology stack, including document ingestion, AI/LLM pipelines, backend services, databases, APIs, and modern web applications. This role is ideal for someone who enjoys solving difficult engineering problems and wants significant ownership over architecture and implementation.

What You'll Do

• Design and build robust document ingestion and processing pipelines.
• Build systems for ingesting PDFs, Word documents, spreadsheets, images, emails, and other unstructured data.
• Develop document parsing, OCR, classification, extraction, chunking, indexing, and retrieval workflows.
• Build and integrate LLM-powered applications and AI agents.
• Develop RAG systems and intelligent search/retrieval capabilities.
• Design scalable backend services and APIs.
• Build modern frontend applications and interfaces for AI-powered workflows.
• Work across the full stack from data ingestion through the user experience.
• Evaluate and integrate new AI models, frameworks, and technologies.
• Write clean, maintainable, well-tested production code.
• Build monitoring, evaluation, logging, and quality-control systems for AI applications.
• Optimize systems for accuracy, speed, scalability, and cost.
• Troubleshoot complex technical and data-quality problems.
• Work closely with company leadership to turn product ideas into production systems.

What We're Looking For

• Strong software engineering and coding ability.
• 3+ years of professional software engineering experience.
• Strong experience with Python and/or another modern backend language.
• Hands-on experience building production AI/ML applications.
• Experience with document ingestion, document processing, or document intelligence.
• Experience working with PDFs, OCR, document parsing, extraction, or unstructured data.
• Strong understanding of LLMs, embeddings, vector search, RAG, and AI application architecture.
• Experience building APIs and backend services.
• Strong full-stack development experience.
• Experience with React, TypeScript, Next.js, or comparable technologies.
• Experience with relational and/or NoSQL databases.
• Strong Git, testing, debugging, and software-development practices.
• Ability to take ownership of projects and work independently.

Highly Valuable

• Experience with Unstructured, LlamaParse, Docling, Apache Tika, PyMuPDF, or similar document-processing technologies.
• Experience with AWS Textract, Google Document AI, Azure Document Intelligence, Tesseract, or similar OCR/document-AI systems.
• Experience with OpenAI, Anthropic, Gemini, or other frontier LLM APIs.
• Experience with Pinecone, Weaviate, Qdrant, pgvector, or other vector databases.
• Experience building AI agents and multi-step AI workflows.
• Experience with AWS, Azure, or GCP.
• Experience with Docker and CI/CD.
• Experience designing systems that process large document collections.
• Experience optimizing AI systems for latency, cost, accuracy, and reliability.