Senior Backend Engineer (Python | FastAPI | AI Document Processing) at Phitech Labs Pvt Ltd | Torre
Senior Backend Engineer (Python | FastAPI | AI Document Processing)
Report
Phitech Labs Pvt Ltd

Senior Backend Engineer (Python | FastAPI | AI Document Processing)

Phitech Labs Pvt Ltd
Emma
Emma
You'll architect AI-driven document processing systems, transforming large-scale data into intelligent insights.
Emma highlights
This highlight was written by Emma’s AI. Ask Emma to edit it.
Full-time

Legal agreement: Employment

Provide your expected compensation while applying
location_on
Remote (anywhere)
Match
skeleton-gauges
You have opted out of job matches in .
To undo this, go to the 'Skills and Interests' section of your preferences.
Review preferences
Shared by
Cata Morales
 8 days ago

Requirements and responsibilities

We are looking for an experienced Senior Backend Engineer to join an exciting AI-driven document processing project opportunity.Design & build scalable document processing backend systems using Python & FastAPIDevelop AI-based document classification systems using taxonomy & confidence scoringHandle large-scale PDF processing and multi-page document assembly workflowsIntegrate OCR engines (Textract / Tesseract / Azure Form Recognizer / Document AI, etc.)Implement LLM-based document extraction and classification (GPT-4 Vision preferred)Build asynchronous workflows using queues, background workers, and event-driven architectureDesign robust error handling, audit trails, and data lineage systemsOptimize system performance for high-volume document processing (10K+ documents)Work with GCP services (Cloud Run, Pub/Sub, Cloud Storage, Firestore, Cloud Tasks)Drive system design decisions for scalability, reliability, and cost efficiencyRequired Skills:8–10 years of strong hands-on experience in Python & FastAPI6–8 years of experience in OCR / Document Processing systemsStrong experience in high-volume document processing pipelinesHands-on experience with OCR tools (Tesseract / Textract / Azure Form Recognizer / Google Document AI, etc.)Strong experience in PDF processing libraries (PyPDF2, pdf2image, etc.)Experience integrating LLMs for document classification or extractionStrong knowledge of async systems, queues, and event-driven architectureHands-on experience with GCP services (Cloud Run, Pub/Sub, Cloud Storage, Firestore, Cloud Tasks)Strong understanding of system design, scalability, and observabilityNice to Have:Experience in financial services / compliance / lending domainExperience with taxonomy design & document classification systemsKnowledge of confidence scoring & validation frameworksExperience with audit trails, data lineage, and versioning systemsExposure to AI/ML-based document intelligence platformsWhat We’re Looking For:Strong backend engineering mindset (system thinking > API development)Experience building document intelligence or OCR-based systemsAbility to handle large-scale asynchronous processing systemsStrong ownership of failure scenarios, edge cases, and scalability challengesExperience in AI-assisted backend architectureShift: 5:30 PM – 2:30 AM IST. Notice Period: Immediate Joiners Only.📩 Interested candidates can apply mail id: syed.faizan@phitechlabs.com
Closes in:
0
days
0
hours
0
min
0
sec
Optionally, you can add more information later (benefits, pre-screening questions, etc.)

Thank you

Thank you

check_circle

Payment confirmed

Torre Hunt

Torre Hunt

A member of the Torre team will contact you shortly

In the meantime, continue adding information to your job opening.