Artificial Intelligence / LLM Architect - Delhi

Amantya Technologies; New Delhi; On-site; INR 4,000,000 - 7,000,000; Full time

Job summary

Amantya Technologies is seeking a Senior AI/LLM Architect to design enterprise agentic applications for knowledge processing and ingestion of government documents. The role focuses on RAG, anomaly detection, and semantic search across large repositories.

You will fine-tune LLMs for policy-domain use cases, develop explainable AI features, and build scalable APIs for model integration in secure environments.

Qualifications

• Bachelor's or Master's degree in CS/AI/DS or related field.
• 6–12 years of software engineering and AI/ML experience.
• Minimum 5 years hands-on in LLM, RAG, NLP, or Generative AI solutions.
• Experience designing enterprise-scale AI platforms for large document repos.
• Experience in government/public sector or regulated domains is preferred.

Responsibilities

• Design and implement enterprise Agentic Applications for knowledge processing.
• Develop knowledge ingestion pipelines for structured and unstructured government documents.
• Build semantic search and retrieval systems using vector databases and search engines.
• Develop anomaly detection models to identify contradictions and policy deviations.
• Develop Intent Management Systems to understand documents.
• Fine-tune and optimize LLMs for government and policy-domain use cases.
• Develop explainable AI capabilities, confidence scoring, and audit trails.
• Build APIs and microservices for AI model integration.

Skills

AI/ML

LLMs

RAG

Semantic similarity

Text classification

Anomaly detection

Vector databases

Search technologies

Python

PyTorch

TensorFlow

LangChain

LlamaIndex

Education

Bachelor's or Master's in CS/AI/DS

Tools

Milvus

Qdrant

Weaviate

Elasticsearch/OpenSearch

Hybrid Search

LlamaIndex

Job description

Job Description AI/LLM Expert (RAG & Anomaly Detection Platform)

Position : Senior AI/LLM Architect – RAG, Knowledge Intelligence & Anomaly Detection

Key Responsibilities

• Design and implement enterprise Agentic Applications for knowledge processing.
• Develop knowledge ingestion pipelines for structured and unstructured government documents.
• Build semantic search and retrieval systems using Vector Databases and Search Engines.
• Develop anomaly detection models to identify contradictions, policy deviations, and historical inconsistencies.
• Develop Intent Management Systems to understand Documents.
• Fine-tune and optimize LLMs for government and policy-domain use cases.
• Develop explainable AI capabilities, confidence scoring, and audit trails.
• Build APIs and microservices for AI model integration.

Mandatory Technical Skills

• AI / Machine Learning
• Understanding and Integration with Open source Large Language Models (LLMs) like Llama, Mistral, Gemma
• Retrieval-Augmented Generation (RAG)
• Semantic Similarity & Text Classification
• Semantic anomaly detection
• Vector Databases (Milvus, Qdrant, Weaviate)
• Search Technologies like Elasticsearch / OpenSearch & Hybrid Search (Keyword + Semantic Search)
• Python/PyTorch / TensorFlow
• LangChain / LlamaIndex

Experience Requirements

• Bachelor's or Master's degree in Computer Science, AI, Data Science, or related field.
• 6–12 years of software engineering and AI/ML experience.
• Minimum 5 years of hands-on experience in LLM, RAG, NLP, or Generative AI solutions.
• Experience designing enterprise-scale AI platforms handling large document repositories.
• Experience with government, public sector, legal, regulatory, telecom, banking, or compliance-related domains preferred.

Experience with on-premise deployments and security-sensitive environments is highly desirable