We are looking for a hands-on Senior GenAI / Agentic AI Engineer to design and build an AI-powered data consolidation and intelligent document-processing platform.

The solution will process large volumes of structured, semi-structured and unstructured information received through documents, scanned files, images, forms and other manual-input sources. It must automatically classify documents, extract relevant information, identify and match the correct entities, validate the extracted data and map it to the appropriate database schema, tables and columns.

The ideal candidate will combine robust Generative AI and agentic workflow experience with intelligent document processing, AWS cloud services, data engineering and database integration.

KEY RESPONSIBILITIES

- Design and develop an end-to-end AI-powered document ingestion and data-consolidation platform.
- Process large volumes of PDFs, scanned documents, images, forms, tables and other unstructured content.
- Implement OCR and multimodal AI capabilities to extract text, tables, key-value pairs and document-layout information.
- Build document-classification and field-extraction workflows using LLMs, vision-language models and document AI services.
- Develop agentic AI workflows using LangGraph, LangChain or similar orchestration frameworks.
- Create specialized agents for document classification, information extraction, validation, entity matching, schema mapping and exception handling.
- Use Amazon Bedrock and Claude models to process, reason over and structure document content.
- Develop effective system prompts,



structured-output prompts and validation strategies for reliable JSON/schema-compliant responses.
- Map AI-extracted information to the appropriate business entities, database schemas, tables and columns.
- Implement entity resolution, record linkage, fuzzy matching, deduplication and master-data matching.
- Develop validation rules, confidence-scoring mechanisms and human-in-the-loop workflows for low-confidence or ambiguous records.
- Integrate AI workflows with relational databases, APIs, data lakes and downstream enterprise applications.
- Design scalable data collection, ingestion, transformation and consumption pipelines.
- Contribute to AWS data-lake/lakehouse architecture using services such as Amazon S3, AWS Glue, Lake Formation, Athena, Redshift or Databricks.
- Use Amazon Bedrock AgentCore or equivalent capabilities to deploy, secure, monitor and operate AI agents at scale.
- Use Amazon SageMaker where custom ML model training, fine-tuning, deployment or model lifecycle management is required.
- Implement RAG pipelines and vector search for document retrieval, contextual enrichment and reference-data matching.
- Develop evaluation frameworks for extraction accuracy, hallucination detection, schema compliance and agent performance.
- Implement observability for agent execution, model latency, token consumption, failures, retries and data-quality issues.
- Ensure enterprise-grade security, auditability, access control, PII protection and regulatory compliance.
- Collaborate with data architects, data engineers, database teams, AI/ML engineers and business stakeholders.
- Take solutions from proof of concept through production deployment and operational support

📌 Excellent Opportunity For AI Engineers For Bengaluru Location
🏢 Nous Infosystems
📍 Bengaluru