AI Software Engineer — Python, Document Intelligence & AWS (Remote)

AI Software Engineer — Python, Document Intelligence performs OCR and Python-based processing; structures and indexes the resulting information; and makes the data searchable and usable by modern LLMs. We are looking for a strong builder , not someone whose AI experience consists primarily of calling an LLM API. You should be comfortable jumping directly into an existing project, understanding the architecture, debugging difficult data-processing problems, and shipping production code. What You’ll Work On Build production systems primarily in Python Build and improve large-scale document ingestion pipelines Process PDFs, scans, images, HTML, and other file formats Build OCR and document-intelligence workflows Classify incoming documents and route them through appropriate processing pipelines Build Python post-processing to clean, normalize, validate, and structure extracted information Solve large-file processing issues using chunking, queues, parallel processing, retries, and recovery Extract text, tables, entities, metadata, relationships, and structured records Build ETL and asynchronous data-processing pipelines Build hybrid search, vector search, embeddings, RAG, and reranking Integrate Claude, OpenAI, Gemini, Qwen, and other LLMs Build evidence and citation systems connecting AI outputs to original source material Build and maintain production infrastructure in AWS Work with PostgreSQL, OpenSearch, S3, queues, caching, and APIs Build integrations including authentication, webhooks, Stripe, and third-party services Write tests for OCR, extraction, retrieval, data processing, APIs, and AI outputs Diagnose production failures and improve system reliability and performance Core Technical Skills Python: FastAPI, data processing, ETL, APIs, asynchronous/background jobs Document Intelligence: OCR, PDF parsing, scanned documents, OpenCV, PyMuPDF, PaddleOCR, Tesseract, Docling, Unstructured, or similar tools AI: Claude, OpenAI, Gemini, Qwen, RAG, embeddings, structured outputs, reranking, model orchestration Data: PostgreSQL, SQL, OpenSearch/Elasticsearch, vector databases, Redis AWS: S3, RDS, OpenSearch, Bedrock, EC2/ECS/EKS, Lambda, SQS, IAM, CloudWatch Infrastructure: Docker, Linux, CI/CD, production cloud deployments Frontend experience with React, Next.js, and TypeScript is helpful but is not the primary focus. Who We Want We want someone who can be given a difficult engineering problem and figure it out. For example: “We have several thousand pages across PDFs, scans, images, and other file formats. Large files are processing inconsistently. Build a reliable AWS pipeline that classifies the files, performs OCR where required, cleans and structures the output with Python, handles failures, indexes the information, and makes the evidence usable by an LLM.” You should be able to break a problem like the one above into an architecture and then actually build it. Strong candidates will have experience building real production systems involving Python, data pipelines, OCR/document processing, AWS, or AI. Requirements Must be based in New York City Must be a U.S. citizen Must be available approximately 40 hours per week Strong Python engineering ability Production AWS experience Experience with OCR, document processing, data engineering, or similar high-volume processing systems Experience integrating modern LLMs Strong backend/API/database fundamentals Comfortable independently debugging complex engineering problems Able to meet with our team in person in NYC Able to complete a technical engineering screen Interview Process We are intentionally keeping the process straightforward: 1. Application Review — Resume, LinkedIn, GitHub, and/or examples of systems you have built. 2. Technical Screen — Python, OCR/document processing, AWS, data architecture, and LLM engineering. 3. In-Person NYC Meeting — Meet the team, walk through the project, and discuss how you would approach real engineering problems from the platform. We are looking for someone who can join quickly, take ownership, and immediately contribute to a technically ambitious production AI system. About NextGen Coding Company NextGen Coding Company is a U.S.-based software engineering firm building custom software, AI systems, automation platforms, data infrastructure, and enterprise applications. Our engineers work on real production systems across AI/ML, document intelligence, data engineering, financial and compliance technology, and cloud infrastructure. To Apply Please send: Resume or LinkedIn GitHub and/or portfolio, if available A short description of the most technically difficult production system you have built Any relevant experience with Python, OCR/document processing, AWS, and LLMs NYC candidates only.