Machine Learning Ai Engineer

Arkesha Desai - AI Engineer Resume

Authorized to work in the US

LinkedIn Profile: www.linkedin.com/in/arkesha-desai-5ab965177 Email: ************@*****.*** Phone: +1-626-***-**** Location: Pasadena CA Professional Summary

AI Engineer and Machine Learning Expert with strong Python programming skills and extensive experience in Natural Language Processing (NLP), Large Language Models (LLMs), and vector databases. Proficient in using cloud platforms like AWS and Azure for AI service deployment and containerization. Hands-on experience with LLM frameworks such as LangChain, and Hugging Face pipelines for text classification and entity extraction. Adept at prompt engineering, retrieval-augmented generation (RAG) systems, and vector databases like Pinecone and Qdrant.

Technical Skills

- Programming Languages: Python, Jupyter Notebooks

- Data Science & Analysis: Pandas, Matplotlib, Scikit-learn

- Natural Language Processing (NLP): Hugging Face Pipelines, Text Classification, Entity Extraction, Text Generation

- LLM & Semantic Search: Langchain, LLamaIndex, Retrieval-Augmented Generation (RAG), Prompt Engineering

- Cloud Platforms: AWS, Google Cloud (AI technologies), Azure AI (Azure OpenAI Service, Azure AI Search, Azure Document Intelligence)

- Vector Databases: Pinecone, Qdrant, Weaviate, Vespa

- Containerization: Docker, Kubernetes

- MLOps & DevOps: Azure DevOps, CI/CD Integration, AI resource management, Cost Optimization

Professional Experience

Machine Learning Engineer

Crazy Sofnet Technologies, India September 2022 – Present

- Developed retrieval-augmented generation (RAG) systems using LangChain and Hugging Face for improved search and text generation.

- Built and deployed NLP models for tasks such as text classification and entity extraction using Hugging Face pipelines.

- Integrated Azure OpenAI services into AI systems, provisioning and managing Azure AI resources with a focus on cost management and security best practices.

- Utilized vector databases like Pinecone for efficient similarity search and retrieval in AI-driven applications.

- Containerized ML models using Docker and deployed them on Azure for scalable, efficient solutions.

Key Projects

- RAG System for Semantic Search: Developed a semantic search and retrieval system using LangChain and Pinecone, enabling accurate document retrieval with retrieval-augmented generation techniques.

- NLP Text Classification & Entity Extraction: Implemented NLP pipelines using Hugging Face for text classification and named entity recognition (NER) across large datasets.

- Prompt Engineering for LLMs: Designed and structured prompts programmatically using OpenAI APIs for LLM tasks, focusing on effective query design and prompt optimization.

Contact this candidate