Experience Skills

- 6-10 years of software engineering experience, including 2+ years building and operating production retrieval and Document AI systems.
- Proven experience building production RAG systems at scale, handling 100K+ documents and millions of chunks, with a strong understanding of retrieval quality, latency and scalability.
- Strong Python development skills, particularly Python 3.11+ and FastAPI, with experience building production-grade APIs and services.
- Solid understanding of document processing pipelines, including chunking, metadata extraction, embeddings and indexing, and hands-on experience with document parsing, OCR and Vision Language Models (VLMs) across PDF, PPTX and DOCX formats.
- Experience implementing hybrid retrieval using dense/vector search and BM25, along with rank fusion and reranking strategies.
- Strong understanding of retrieval and RAG evaluation,



including REMAIL_ADDRESS, nDCG/MRR and groundedness, with experience using evaluation metrics to improve retrieval quality.
- Experience with AWS S3, ECS/EKS, Lambda, Bedrock, Textract and OpenSearch, and familiarity with cloud-native AI architectures.
- Proficiency with Docker, pytest, Git and CI/CD, with strong engineering practices around testing, automation and production reliability. Life Sciences, Healthcare or Pharma experience preferred.

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.

📌 Consultant - Gen AI Architect (Sr RAG - Document AI Engineer) (Hyderabad)
🏢 CHRYSELYS
📍 Hyderabad