Design, develop, and deploy Generative AI and LLM-based applications using Python, including enterprise-grade AI solutions and intelligent assistants
Build and optimize Retrieval-Augmented Generation (RAG) pipelines using LangChain and/or LlamaIndex, integrating enterprise data sources with LLMs.
Develop scalable data engineering and ETL pipelines using Python and SQL to ingest, transform, and prepare structured and unstructured data for AI applications.
Implement and optimize Vector Database solutions for embeddings, semantic search, document retrieval, and contextual information retrieval.
Deploy and operationalize GenAI/LLM solutions on AWS, Microsoft Azure, or Google Cloud Platform (GCP) using MLOps/LLMOps practices, including monitoring, versioning, CI/CD, model lifecycle management, and production support.
Job Skills/Competencies Required
Your Profile
Strong hands-on experience in Python and SQL, with solid knowledge of software development, data processing, and API-based integrations.
Proven experience working with Generative AI, Large Language Models (LLMs), RAG architectures, prompt engineering, embeddings, and LLM application development.
Hands-on expertise with LangChain and/or LlamaIndex and experience integrating LLMs with Vector Databases such as Pinecone, FAISS, Chroma, Weaviate, Milvus, or equivalent technologies.
Strong understanding of Data Engineering, ETL, data pipelines, structured/unstructured data processing, and cloud services on AWS, Azure, or GCP.
Experience with MLOps/LLMOps, including model/application deployment, CI/CD, monitoring, evaluation, version control, scalability, security, and productionization of AI solutions.
