Back
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Niche RAG/Document-AI skills limit applicants, but mid-senior software title attracts competition.
Core GenAI and retrieval skills transfer across industries, though pharma experience preference increases domain specificity.
Explicit 6–10 years, 2+ years RAG experience, plus strict tech stack and production reliability requirements.
Build and operate production-scale Retrieval-Augmented Generation (RAG) systems processing 100K+ documents with millions of chunks, ensuring retrieval quality, latency, and scalability.
Develop and maintain document AI services including parsing, OCR, vision language models, chunking, metadata extraction, embeddings, indexing, and hybrid retrieval techniques.
Implement and improve evaluation strategies using metrics like Recall@K, nDCG/MRR, and groundedness to enhance retrieval quality on cloud-native AI architectures leveraging AWS services.
6–10 years of software engineering experience with at least 2 years in production retrieval and Document AI systems.
Strong Python development skills with Python 3.11+ and FastAPI for production-grade API/service development.
Experience with document parsing/OCR (PDF, PPTX, DOCX) and building retrieval pipelines including vector/dense search and BM25 hybrid retrieval.
Experience working with AWS cloud services (S3, ECS/EKS, Lambda, Bedrock, Textract, OpenSearch) and tools like Docker, pytest, Git, and CI/CD.
Experienced in scaling and optimizing RAG systems for high document volume and complex retrieval workloads.
Strong engineering discipline with focus on testing, automation, and production reliability in cloud-native environments.
Prior exposure or domain experience in Life Sciences, Healthcare, or Pharma preferred but not mandatory.