About Pryon:
We’re a team of AI, technology, and language experts whose DNA lives in Alexa, Siri, Watson, and virtually every human language technology product on the market. Now we’re building an industry-leading knowledge management and Retrieval-Augmented Generation (RAG) platform. Our proprietary, cutting-edge natural language processing capabilities transform unstructured data into meaningful experiences that increase productivity with unmatched accuracy and speed.
The Opportunity:
The Ingestion team is responsible for everything that happens between content arriving from a connector and that content being ready for search and retrieval. This means document processing pipelines that handle parsing, text extraction, chunking, metadata enrichment, embedding generation, and index population — across every file format and content type our customers throw at us.
We’re in the middle of a significant architectural evolution — migrating from a legacy pipeline to a modern, workflow-orchestrated architecture with cleanly separated processing stages: intake, transformation, enrichment, and indexing. The team is also actively designing the next iteration of the pipeline to push further on throughput and resilience.
This is real systems engineering: the problems are about scale, reliability, and the messy realities of processing millions of documents with wildly different structures.
The Ideal Candidate:
Is self-driven and comfortable operating with autonomy inside a structured team
Gets energized by architectural challenges, not just feature work
Has the patience and discipline to improve existing systems while building new ones
Understands that pipeline engineering is about handling the 10,000 edge cases, not just the happypath
Is motivated by the mission: building the processing backbone that makes enterprise AI accurateand reliable
Communicates well in a remote-first environment and collaborates naturally across teamboundaries
In This Role You Will:
Design and build pipeline stages for our modern ingestion architecture - from document intake through embedding generation and index writing
Contribute to the design of next-generation pipeline architecture as the system evolves
Improve system stability and scale: identify bottlenecks, reduce failure rates, and build observability into every stage
Work with workflow orchestration tools to manage complex, multi-step document processing with retry logic, error handling, and state management
Handle the realities of document diversity: PDFs, HTML, Office formats, images, structured and semi-structured data - all flowing through the same pipeline
Collaborate with the Connectors team (upstream) and Retrieval team (downstream) to ensure data flows cleanly across system boundaries
Participate in the ongoing migration from legacy systems, balancing new development with operational stability
What You'll Need to Be Successful:
5+ years of software engineering experience, with meaningful time on data processing pipelines, ETL systems, or similar infrastructure
Strong proficiency in Python and/or Go
Experience with workflow orchestration tools — Temporal, Airflow, Prefect, Step Functions, or similar
Understanding of distributed systems patterns: queues, workers, backpressure, idempotency, retry strategies
Hands-on experience with Kubernetes, Docker, Terraform, and Helm
Familiarity with message brokers and event streaming (Kafka, RabbitMQ, SQS, or similar)
Comfort working across cloud providers (AWS, Azure, GCP)
