Overview

We have the open positions for the Remote location. Kindly review the details below:

• Experience: 6 years
• Location: Remote
• Timings: 5.30pm to 2.30am

Key Responsibilities

• LargeScale Document Intelligence Pipelines
  • Design and build endtoend pipelines for processing longform, OCRheavy documents
  • Own PDF ingestion, layoutaware parsing, and multipage document assembly
  • Implement robust chunking, segmentation, and metadata tracking across long documents
  • Handle exception detection, retries, and deterministic failure handling
  • Optimize systems to reliably process 200+ page documents at scale
• OCR & Structured Extraction Systems
  • Work with OCR engines (Tesseract, PaddleOCR, layoutaware models, visionlanguage models)
  • Build layoutaware extraction systems using bounding boxes and structural metadata
  • Implement deterministic schema validation and crossfield consistency checks
  • Reduce reliance on manual QA through rulebased validation layers
  • Ensure traceability from extracted field back to source span
• SelfHosted LLM Inference (Production Ownership)
  • Deploy and operate opensource LLMs using:
  • vLLM
  • Hugging Face TGI
  • GPUbacked serving stacks
  • Tune inference performance:
  • KV cache management
  • Batching
  • Context window control
  • Throughput vs latency tradeoffs
  • Monitor and optimize GPU utilization and cost per request
  • Own production reliability of LLM serving infrastructure
• Deterministic Validation & Control Systems
  • Design validation layers outside the LLM
  • Implement schema enforcement, rule engines, invariants, and rejection logic
  • Build automated exception routing without default human review
  • Ensure auditability and reproducibility of extraction results
  • Create measurable correctness guarantees for highstakes use cases