Senior Software Engineer, Document Intelligence & Data Infra

Unusual Ventures; New York (NY); On-site; USD 150,000 - 230,000; Full time

Job summary

Helios seeks a Staff/Senior Software Engineer to build and operate large-scale ingestion and document-processing systems in production. You will expand Proxi’s capabilities across multilingual data sources, document formats, and secure environments, enabling end-to-end processing from source to publication.

The role emphasizes multilingual processing, OCR/layout analysis, and real-time audio transcription, with work across CPU/GPU workloads in cloud and air-gapped setups.

Qualifications

• Experience building large-scale acquisition or document-processing systems in production.
• Ability to handle multilingual data and sources.
• Experience with document conversion, OCR, layout analysis, and extraction.
• Experience maintaining secure, observable, scalable processing systems in cloud and restricted environments.

Responsibilities

• Expand Proxi’s ingestion and document-processing platform from source acquisition through downstream publication.
• Construct crawling and connector infrastructure to discover, acquire, and maintain international data sources.
• Scale the distributed processing environment that supports document conversion, extraction, transcription, enrichment, replay, and backfills.
• Establish common data contracts that normalize heterogeneous and multilingual sources without discarding jurisdictional context or provenance.
• Maintain pipeline reliability, security, observability, and cost efficiency while ensuring corrections propagate downstream.
• Build and operate real-time audio intelligence pipelines for low-latency multilingual transcription, speaker attribution, timestamp alignment, confidence-calibrated tone analysis across live and recorded media.

Skills

Web crawlers

Fault-tolerant pipelines

Multilingual document processing

OCR & layout analysis

Data provenance

Secure processing

CPU/GPU processing

Real-time audio transcription

Job description

Helios seeks a Staff/Senior Software Engineer to build and operate large-scale ingestion and document-processing systems in production. You will expand Proxi’s capabilities across multilingual data sources, document formats, and secure environments, enabling end-to-end processing from source to publication.

The role emphasizes multilingual processing, OCR/layout analysis, and real-time audio transcription, with work across CPU/GPU workloads in cloud and air-gapped setups.