Data Scientist

Job Summary As a Generative AI Engineer at Cyient , you will play a pivotal role in designing, developing, and deploying enterprise-scale AI solutions powered by Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI Agents, and Agentic AI frameworks. You will work closely with cross-functional teams to build intelligent applications that automate workflows, enhance decision-making, and accelerate digital transformation across engineering and enterprise domains. You will leverage cutting-edge AI technologies, cloud platforms, and backend engineering principles to deliver scalable, secure, and production-ready AI systems. Job Responsibilities Design, develop, and deploy enterprise-grade Generative AI applications using Large Language Models (LLMs) such as GPT, Claude, and open-source models. Build and optimize Retrieval-Augmented Generation (RAG) pipelines, including document ingestion, chunking, embedding generation, vector indexing, and hybrid search. Develop AI Agents and multi-agent workflows using frameworks such as LangChain, LangGraph, Microsoft Agent Framework, or similar orchestration platforms. Integrate enterprise applications and external tools using Model Context Protocol (MCP), function calling, and API orchestration. Fine-tune open-source LLMs using LoRA, QLoRA, PEFT, and Hugging Face Transformers to improve domain-specific performance. Design scalable backend services and REST APIs using Python (FastAPI) and/or Java Spring Boot to support AI applications. Deploy AI workloads on Azure, AWS, or GCP using Docker, Kubernetes, and CI/CD pipelines. Build and maintain vector databases, semantic search, and hybrid retrieval systems using FAISS, Pinecone, Chroma, Weaviate, or Azure AI Search. Implement LLM evaluation and monitoring using frameworks such as LangSmith, RAGAS, DeepEval, MLflow, and Prometheus/Grafana. Collaborate with product managers, solution architects, data engineers, and domain experts to translate business requirements into AI-powered solutions. Optimize AI applications for latency, scalability, security, and production reliability. Stay current with advancements in Generative AI, Agentic AI, multimodal AI, and emerging LLM technologies, and evaluate their applicability to enterprise use cases. Contribute to AI architecture, best practices, reusable frameworks, and coding standards across the organization. Document AI solutions, deployment architectures, and technical designs while mentoring junior engineers where applicable. Job Qualifications Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Data Science, Electronics, Information Technology, or a related engineering discipline. 6+ years of professional experience in Generative AI, AI/ML, or backend software engineering. Strong proficiency in Python and/or Java , with experience developing scalable backend applications. Hands-on experience with Large Language Models (LLMs) and enterprise AI application development. Strong knowledge of LangChain, LangGraph, AI Agents, Agentic AI, Prompt Engineering, Context Engineering, and RAG architectures . Experience with OpenAI API, Azure OpenAI Service, Anthropic Claude API, Hugging Face Transformers , or similar LLM platforms. Practical experience in LoRA, QLoRA, PEFT , model fine-tuning, quantization, and local model deployment using vLLM or similar inference engines. Experience with vector databases such as FAISS, Chroma, Pinecone, Weaviate, or Azure AI Search. Strong understanding of embeddings, semantic search, hybrid search, document processing, and retrieval optimization. Experience building REST APIs using FastAPI , Spring Boot , or similar frameworks. Experience with cloud platforms such as Azure , AWS , or Google Cloud Platform . Hands-on experience with Docker , Kubernetes , Git , and CI/CD pipelines (GitHub Actions, Jenkins, Azure DevOps). Familiarity with event-driven architectures using Kafka or similar messaging platforms. Experience implementing LLM observability, tracing, evaluation, and monitoring using LangSmith , RAGAS , DeepEval , MLflow , Prometheus , and Grafana . Good understanding of software engineering principles, microservices architecture, API security (OAuth2/JWT), and scalable system design.