About Careertakes

👉 Important disclosure: Careertakes is a third-party recruiting platform supporting this hiring process. If selected, you will be employed directly by our client, IT Services & Consulting; Data Infrastructure & Analytics; Software Development.

Applicants for this role may also receive access to additional matched opportunities through the Careertakes platform.

---

Overview

This role is for an experienced AI Software Engineer to join a confidential client’s enterprise AI project focused on large-scale document intelligence and evidence-backed AI analysis. You will contribute hands-on to production Python systems that ingest and process thousands of pages (PDFs, scans, images, HTML), perform OCR, structure and index extracted data, and make it usable for modern LLMs and retrieval systems.

---

What You’ll Work On

• Build production systems and services primarily in Python.
• Design and improve large-scale document ingestion pipelines.
• Process PDFs, scanned documents, images, and HTML; build OCR and document-intelligence workflows.
• Classify and route incoming documents into appropriate processing pipelines.
• Implement Python post-processing to clean, normalize, validate, and structure extracted information.
• Solve large-file processing problems with chunking, queues, parallelism, retries, and recovery.
• Extract text, tables, entities, metadata, relationships, and structured records.
• Build ETL and asynchronous data-processing pipelines.
• Implement hybrid search, vector search, embeddings, RAG, and reranking systems.
• Integrate multiple LLMs (Claude, OpenAI, Gemini, Qwen, etc.) and orchestrate model usage.
• Build evidence/citation systems linking AI outputs to source material for auditable results.
• Operate and maintain production infrastructure in AWS.
• Work with PostgreSQL, OpenSearch/Elasticsearch, S3, queues, caching, and HTTP APIs.
• Build and maintain integrations (authentication, webhooks, Stripe, third-party services).
• Write tests for OCR/extraction, retrieval, data processing, APIs, and AI outputs.
• Diagnose production failures and improve reliability and performance.

---

Core Technical Skills

• Strong Python engineering (FastAPI, async/background jobs, ETL).
• Document intelligence: OCR, PDF parsing, scanned-doc workflows, OpenCV, PyMuPDF, PaddleOCR, Tesseract, Unstructured or similar.
• Experience with LLMs, embeddings, RAG, reranking, and model orchestration.
• Data skills: PostgreSQL, SQL, OpenSearch/Elasticsearch, vector databases, Redis.
• AWS production experience: S3, RDS, OpenSearch, EC2/ECS/EKS, Lambda, SQS, IAM, CloudWatch.
• Infrastructure & tooling: Docker, Linux, CI/CD, production cloud deployments.
• Frontend experience (React/Next.js/TypeScript) is a plus but not required.

---

Who We’re Looking For

We want a strong builder — someone who can take a difficult engineering problem, design an architecture, and ship reliable production code. Ideal candidates have hands-on experience building production systems involving Python, high-volume document processing/OCR, scalable data pipelines, AWS, and integrating modern LLMs.

Example challenge you should handle: “We have several thousand pages across PDFs, scans, images, and other file formats. Large files process inconsistently. Build a reliable AWS pipeline that classifies files, performs OCR, cleans and structures output with Python, handles failures, indexes the information, and makes the evidence usable by an LLM.”

---

Requirements

• Must be based in New York, NY and able to meet in person with the team in NYC when required.
• Must be authorized to work in the U.S. without sponsorship and able to complete a W-9. (No visa sponsorship available.)
• Availability for approximately 40 hours per week.
• Strong proven Python engineering ability and experience shipping production services.
• Production AWS experience and familiarity with S3, RDS, OpenSearch, etc.
• Experience with OCR, high-volume document processing, or data engineering pipelines.
• Experience integrating modern LLMs and building retrieval/embedding workflows.
• Strong backend, API, and database fundamentals.
• Comfortable independently debugging complex engineering problems.
• Able to complete a technical engineering screening.

---

Interview Process

• Application review — resume, GitHub, portfolio, or examples of systems you’ve built.
• Technical screen — topics include Python, OCR/document processing, AWS, data architecture, and LLM engineering.
• In-person NYC meeting — walk the team through projects and how you would approach real production problems.

---

About the Client

The confidential client is a U.S.-based software engineering firm working across AI/ML, document intelligence, data engineering, automation platforms, and enterprise applications. Their engineering teams build production systems focused on data infrastructure, compliance, and cloud-native AI deployments.

---

Equal Opportunity & Hiring Transparency

Careertakes and our client are Equal Opportunity Employers committed to building a diverse and inclusive workforce. We prohibit discrimination or harassment of any kind. To support a fair and efficient hiring process, AI tools may be used to assist with application review or resume screening. These tools do not replace human decision-making. Final hiring decisions are made by people.

If you have questions about how your data is used, please contact us directly.