07/10/2026 updated
100 % available
AI / ML Engineer | LLM & Generative AI Specialist | Python | RAG Pipelines | MLOps
New Delhi, India
Only remote
Bachelor's in Computer ApplicationArtificial IntelligenceMachine LearningAzure Machine LearningGenerative AIMachine Learning OperationsArtificial Intelligence Markup Language (AIML)Data Pipeline
Machine Learning & Predictive Modeling
Expertise in developing and optimizing machine learning models including regression models, predictive modeling, model quantization, feature engineering, and model evaluation and monitoring for production-grade AI systems.
Generative AI & LLM Engineering
Deep knowledge in building LLM-based applications using OpenAI GPT, LLaMA 3, Qwen, and HuggingFace models, including RAG pipelines, prompt engineering, LLM orchestration, AI agents, and multi-agent systems.
Backend & Data Engineering with Python
Strong proficiency in Python-based backend development using FastAPI, REST APIs, WebSockets, and microservices architecture, enabling scalable and production-ready AI-driven solutions.
AI Frameworks
Hands-on experience with leading AI frameworks including LangChain, LlamaIndex, FastAPI AI Services, and Transformers (HuggingFace) for building and deploying intelligent applications.
Vector Databases
Practical experience with vector database technologies such as Milvus, Qdrant, and FAISS for efficient similarity search and retrieval in RAG-based systems.
Cloud & DevOps / Containerization
Proficiency in containerizing and deploying ML and AI pipelines using Docker, Linux, Git, CI/CD pipelines, and microservice architecture to ensure scalability and production readiness.
Databases
Experience working with relational and vector databases including PostgreSQL, MySQL, and vector database solutions for data storage and retrieval in AI applications.
Computer Vision
Experience in delivering end-to-end face recognition systems integrating computer vision models with production APIs for real-time authentication and identity verification.
Document Intelligence & AI Copilot Systems
Capability in building document intelligence solutions and AI copilot systems leveraging context augmented generation (CAG) and automated document analysis for enterprise applications.
Expertise in developing and optimizing machine learning models including regression models, predictive modeling, model quantization, feature engineering, and model evaluation and monitoring for production-grade AI systems.
Generative AI & LLM Engineering
Deep knowledge in building LLM-based applications using OpenAI GPT, LLaMA 3, Qwen, and HuggingFace models, including RAG pipelines, prompt engineering, LLM orchestration, AI agents, and multi-agent systems.
Backend & Data Engineering with Python
Strong proficiency in Python-based backend development using FastAPI, REST APIs, WebSockets, and microservices architecture, enabling scalable and production-ready AI-driven solutions.
AI Frameworks
Hands-on experience with leading AI frameworks including LangChain, LlamaIndex, FastAPI AI Services, and Transformers (HuggingFace) for building and deploying intelligent applications.
Vector Databases
Practical experience with vector database technologies such as Milvus, Qdrant, and FAISS for efficient similarity search and retrieval in RAG-based systems.
Cloud & DevOps / Containerization
Proficiency in containerizing and deploying ML and AI pipelines using Docker, Linux, Git, CI/CD pipelines, and microservice architecture to ensure scalability and production readiness.
Databases
Experience working with relational and vector databases including PostgreSQL, MySQL, and vector database solutions for data storage and retrieval in AI applications.
Computer Vision
Experience in delivering end-to-end face recognition systems integrating computer vision models with production APIs for real-time authentication and identity verification.
Document Intelligence & AI Copilot Systems
Capability in building document intelligence solutions and AI copilot systems leveraging context augmented generation (CAG) and automated document analysis for enterprise applications.
Languages
EnglishFluent
Project history
Designed and implemented LLM-powered Compliance Copilot (Lexicura) for policy gap analysis, regulatory Q&A, and compliance monitoring using RAG pipelines and vector databases. Developed Passenger Mishandling Prediction System using regression-based ML models improving operational prediction accuracy by 85%. Built RAG-based intelligent chatbots for BFSI clients using LangChain and vector search. Engineered Bid Compliance Automation System leveraging LLMs (Qwen, LLaMA 3.2). Implemented AI-powered Bid Evaluation Engine for automated vendor selection. Developed Credit Underwriting Rule Engine for financial workflows. Built Mascot AI Platform for Skincare Product Testing using OpenAI LLM APIs. Developed AI-powered Outlook Email Assistant for Arada with voice-enabled productivity features. Delivered End-to-End Face Recognition System for real-time authentication. Optimized large-scale ML inference pipelines using model quantization, reducing inference latency by 70%. Containerized and deployed ML and AI pipelines using Docker, Linux, and microservice architecture.