Job Description

About the Role.

As a Full-Stack AI Engineer, you will play a pivotal role in designing, building, and deploying cutting-edge AI systems that power our intelligent applications. You will work across the entire AI stack--from NLP/LLM model development and fine-tuning to production-grade deployment and multi-agent orchestration. This role involves creating high performance entity extraction pipelines, implementing hybrid AI architectures, managing vector and knowledge graph databases, and building smart APIs that integrate seamlessly with AI workflows. You will also work on modern GenAI applications, including prompt engineering, retrieval- augmented generation (RAG) pipelines, and multi-step LLM orchestration, ensuring our AI systems are accurate, reliable, and scalable. This position offers the opportunity to work with state-of-the-art technologies in NLP, LLMs, AI infrastructure, and GenAI, contributing directly to the next generation of intelligent, real-time AI applications.

Key Responsibilities.

Develop hybrid Trie + BERT architectures for high-performance entity extraction. Fine-tune transformer models (BERT, RoBERTa, custom architectures) for domain- specific tasks. Build and maintain LLM-powered verification systems (GPT-4, Claude, and others). Implement tokenless detection, auto-discovery, and AI transformation pipelines. Orchestrate LLM workflows using LangChain, LlamaIndex, or similar frameworks. Build Retrieval-Augmented Generation (RAG) pipelines with vector DBs. Deploy and orchestrate AI agents using Kubernetes and Docker. Manage vector DBs (Pinecone/Weaviate) and knowledge graphs (Neo4j/TigerGraph). Develop smart APIs (GraphQL/REST) and MCP server integration. Apply prompt engineering and structured output techniques for LLMs. Monitor and optimize AI system performance using Prometheus/Grafana. Implement responsible AI practices: hallucination mitigation, evaluation, and safety.

Nice to Have.

Experience with fine-tuning LLMs (LoRA/PEFT) Familiarity with LangChain, LlamaIndex, or similar agent frameworks Knowledge of AI-assisted code generation or AutoML pipelines Background in model evaluation, responsible AI, and content safety
Job Type: Full-time

Pay: ?500,000.00 - ?2,000,000.00 per year

Benefits:

Flexible schedule Health insurance Provident Fund
Application Question(s):

How soon can you join? (No of days) What is your current compensation? What are your compensation expectations?
Work Location: In person