AI Engineer

Role: Data & AI Engineer

We are seeking a talented and detail-oriented Data & AI Engineer to develop and deploy cutting-edge artificial intelligence solutions focused on regulatory compliance. You will play a critical role in leveraging Large Language Models (LLMs) and AWS Bedrock to transform how we manage and interpret critical regulatory data. You should possess excellent communication and collaboration skills, working in a fast-paced agile development environment.

Key Responsibilities

AI Solution Development: Design, develop, and deploy AI solutions, specifically utilizing AWS Bedrock and other LLMs, to achieve regulatory compliance and enhance data insights.

Data Preparation & Embedding: Develop advanced parsing and chunking strategies to handle diverse data sources (Files, APIs, Newsletters, Email Lists, Web pages). Implement processes to embed documents into vector databases efficiently.

Vector Database Management: Manage and maintain vector databases, including adding and utilizing custom metadata to optimize retrieval and relevance.

RAG Implementation: Design and implement Retrieval-Augmented Generation (RAG) systems, focusing on continuous prompt engineering and experimentation to maximize output quality and accuracy.

System Integration: Integrate AI/ML studios and various LLM APIs into our core platform infrastructure and software development workflow.

MLOps and Optimization: Monitor and continuously optimize RAG model performance. Manage and experiment with MLOps workflows using Amazon SageMaker.

Data Storage & Governance: Design and implement robust data storage solutions for sensitive regulatory data, ensuring data integrity, security, availability, and scalability.

Required Skills and Qualifications

Minimum 5 years of industry experience in software development, with significant time spent in cloud infrastructure and DevOps areas.

AI/LLM Expertise: Proven experience developing and deploying solutions using Large Language Models (LLMs) and platforms like AWS Bedrock.

RAG Proficiency: Hands-on experience designing and implementing Retrieval-Augmented Generation (RAG) systems.

Programming Languages: Strong proficiency in Python is essential. Experience with JS and data processing using PySpark is highly desirable.

Vector Databases: Direct experience with administering and utilizing Vector Databases such as Qdrant or OpenSearch.

Data Management: Expertise in SQL for data querying and management.

Tools: Familiarity with Jupyter Notebooks for development and experimentation.

MLOps: Experience with MLOps tools and methodologies.

AI Development Studios: Experience using the latest AI-assisted software development IDEs like Cursor, GitHub Copilot, etc.

Job Type: Full-time

Pay: ₹1,500,000.00 - ₹2,000,000.00 per year

Work Location: In person