Responsibilities

RAG Architecture & Pipeline Design

§ Design and maintain RAG that connects CRM to LLM to provide grounded, fact bases AI responses.

Vector Search & NLP

§ Implement and maintain vector embeddings for entities to enable semantic search and integration with LLM for generative AI features.

MCP Server Development

§ Design and deploy MCP to bridge LLM with existing Data sources for real-time Retrieval.

Generative AI Integration

§ Utilize LLMs to synthesize retrieved data into accurate, user friendly natural language responses.

Performance Optimization

§ Evaluate and optimize the end-to-end latency of search and generation.

Data Analysis

§ Collect, analyze, and interpret large datasets to identify trends, patterns, and insights that can inform business decisions.

Technical Leadership

§ Lead code reviews, ensuring adherence to coding standards, best practices, and quality requirements.

§ Act as a technical point of contact for complex database issues, offering solutions and recommendations to resolve them.

Project Coordination and Stakeholder Collaboration

§ Collaborate with project managers, business analysts, and stakeholders to understand business requirements and translate them into technical solutions.

Quality Assurance and testing

§ Collaborate with QA teams to validate data quality, ensure accuracy, and troubleshoot issues identified during testing.

Continuous Improvement

§ Stay up-to on the latest tools, techniques, and best practices.

§ Identify opportunities for process improvements, optimizations, and automation.

Documentation and Standards

§ Ensure adherence to data governance and regulatory requirements, including security and compliance standards.

Contributing Responsibilities

Design, develop, implement and maintain AI/LLM products to solve specific business use cases.
Implement and maintain vector embeddings for entities to enable semantic search and integration with LLM for generative AI features.
Design and deploy MCP to bridge LLM with existing Data sources for real-time Retrieval.

Design and maintain RAG that connects CRM to LLM to provide grounded, fact bases AI responses.
Explore and understand the CRM data, including customer demographics, behavior, and transactional data.

Develop and train predictive models using various machine learning algorithms and techniques.

Deploy models in production environments, such as CRM systems.

Monitor model performance, identify areas for improvement, and retrain models as necessary.

Generate insights and recommendations based on data analysis and modeling results.

Communicate insights and results to stakeholders, including business leaders.

Identify opportunities to improve CRM data quality, processes, and systems.

Collaborate with project managers, business analysts, and stakeholders to understand business requirements and translate them into technical solutions.