Role description
Role:
Design and Build the GenAI MVP components including document ingestion RAG pipeline and BRD generation
Implement prompt and context engineering for regulatory content Key Outputs: RAG orchestration LangChain LangGraph Prompt templates fewshot examples Working GenAI MVP with document ingestion RAG Knowledge Graph and BRD generation Accurate contextspecific BRD output for the selected FRTB sectionJob Summary Senior Specialist with 7 to 11 years of experience in AI and Generative AI within the BlueverseAI Fundamentals cluster focused on designing finetuning and deploying advanced generative AI models
Job Description :
Develop and implement innovative AI and Generative AI solutions leveraging large language models LLMs such as GPT LLaMA and Claude Design and customize prompts and workflows to efficiently extract and process data from diverse unstructured sources including emails PDFs and meeting notes Finetune AI models using advanced techniques like LoRA to improve model accuracy and performance Collaborate with business stakeholders to translate complex requirements into scalable AIdriven solutions Utilize AI frameworks and libraries such as LangChain Hugging Face Transformers and OpenAI APIs to build robust AI applications Ensure adherence to organizational policies security standards and compliance during AI model development and deployment Continuously research and integrate emerging AI technologies and methodologies to enhance existing systems and workflows
Roles and Responsibilities:
Own MVP scope milestones and ensure stakeholder alignment throughout the project lifecycle Lead overall Generative AI solution design for the MVP aligning business context with RetrievalAugmented Generation RAG architecture Ensure traceability explainability and adherence to MVP scope requirements Build and optimize document extraction and generation workflows using generative AI models Extract structured information from unstructured inputs such as emails PDFs and meeting notes Create and maintain a comprehensive library of prompts and generalized extraction templates Evaluate model performance using taskspecific metrics such as accuracy and completeness Collaborate closely with subject matter experts SMEs for iterative model improvements Deploy AI models on approved infrastructure ensuring model isolation encryption and compliance with security policies Monitor scale and optimize AI models to meet performance regulatory and operational requirements Utilize enterprise integration tools and cloud platforms Azure AWS GCP to support AI model lifecycle management Implement containerization and orchestration technologies like Docker and Kubernetes for scalable deployments Employ MLOps practices including CICD pipelines model versioning monitoring with tools such as Prometheus and Grafana and logging frameworks
Role:
Design and Build the GenAI MVP components including document ingestion RAG pipeline and BRD generation
Implement prompt and context engineering for regulatory content Key Outputs: RAG orchestration LangChain LangGraph Prompt templates fewshot examples Working GenAI MVP with document ingestion RAG Knowledge Graph and BRD generation Accurate contextspecific BRD output for the selected FRTB sectionJob Summary Senior Specialist with 7 to 11 years of experience in AI and Generative AI within the BlueverseAI Fundamentals cluster focused on designing finetuning and deploying advanced generative AI models
Job Description :
Develop and implement innovative AI and Generative AI solutions leveraging large language models LLMs such as GPT LLaMA and Claude Design and customize prompts and workflows to efficiently extract and process data from diverse unstructured sources including emails PDFs and meeting notes Finetune AI models using advanced techniques like LoRA to improve model accuracy and performance Collaborate with business stakeholders to translate complex requirements into scalable AIdriven solutions Utilize AI frameworks and libraries such as LangChain Hugging Face Transformers and OpenAI APIs to build robust AI applications Ensure adherence to organizational policies security standards and compliance during AI model development and deployment Continuously research and integrate emerging AI technologies and methodologies to enhance existing systems and workflows
Roles and Responsibilities:
Own MVP scope milestones and ensure stakeholder alignment throughout the project lifecycle Lead overall Generative AI solution design for the MVP aligning business context with RetrievalAugmented Generation RAG architecture Ensure traceability explainability and adherence to MVP scope requirements Build and optimize document extraction and generation workflows using generative AI models Extract structured information from unstructured inputs such as emails PDFs and meeting notes Create and maintain a comprehensive library of prompts and generalized extraction templates Evaluate model performance using taskspecific metrics such as accuracy and completeness Collaborate closely with subject matter experts SMEs for iterative model improvements Deploy AI models on approved infrastructure ensuring model isolation encryption and compliance with security policies Monitor scale and optimize AI models to meet performance regulatory and operational requirements Utilize enterprise integration tools and cloud platforms Azure AWS GCP to support AI model lifecycle management Implement containerization and orchestration technologies like Docker and Kubernetes for scalable deployments Employ MLOps practices including CICD pipelines model versioning monitoring with tools such as Prometheus and Grafana and logging frameworks