| Gen AI (LLM pipeline) :: Onsite Role :: at Remote, Remote, USA |
| Email: [email protected] |
| From: Sridar, ITechUS [email protected] Reply to: [email protected] Position:: Gen AI (LLM pipeline) Location:: San Jose, CA : Onsite Role :: Duration:: Contract Role Job Description What we need to see: Demonstrated expertise in AI/ML and LLM technologies, including generative Al, Natural Language Processing, and computer vision. Experience building LLMs pipeline using framework like AutoGen, LangChain, Semantic Kernel, LlamaIndex, Azure Al Studio, OpenAl functions and models Hands-on experience with multimodal Al systems, integrating data from various sources such as text and images to build comprehensive and effective Al solutions. Extensive experience in designing and deploying Al models and systems in production environments. Ability to translate business needs into technical solutions. Proficiency in Python and related tools Strong understanding of LLM architectures, training processes, and data requirements Experience with RAG systems, knowledge base construction, and vector databases Familiarity with embedding techniques, similarity search algorithms, and information retrieval concepts Hands-on experience with data cleaning, tagging, and annotation processes (both manual and automated) Strong problem-solving skills and ability to work in a fast-paced, innovative environment Familiarity with MS Azure and its integration in AI/ML pipelines Experience with various vector store technologies and their applications in Al Responsibilities: Design, develop, and evaluate innovative LLM models to solve diverse challenges and opportunities across multiple use-cases using MS Azure services. Understand business problems, and help with defining and implementing a scalable Generative Al platform to solve them. Build large-scale production systems utilizing advanced machine learning and big data technologies. Develop and optimize data processing workflows for chunking, indexing, ingestion, and vectorization for both text and non-text data Benchmark and implement various vector stores, embedding techniques, and retrieval methods Create a flexible pipeline supporting multiple embedding algorithms, vector stores, search types (vector search, hybrid search, etc.) and search ranking Implement and maintain auto-tagging systems and data preparation processes for LLMs Develop tools and pipelines for text and image data cleaning, and refinement Integrate and optimize workflows using Azure Al Search, Azure Al Services, Azure PostgreSQL and various vector store technologies Use advanced prompting techniques to develop and optimize prompts for LLM to ensure model performance, responses quality and accuracy of the Gen Al platform. Contribute to automated model testing and evaluation infrastructure Build automations to create and select the best prompts for any given task Thanks, Sridar G Keywords: artificial intelligence machine learning microsoft Alabama California Gen AI (LLM pipeline) :: Onsite Role :: [email protected] |
| [email protected] View all |
| Thu Oct 31 00:21:00 UTC 2024 |