GenAI Engineer

Role and responsibilities

·      Collaborate with data engineers, data scientists, and stakeholders to understand data requirements, problem statements, system integrations, and RAG application functionalities.

·      Utilize, apply & enhance GenAI models using state-of-the-art techniques like transformers, GANs, VAEs, LLMs (including experience with various LLM architectures and capabilities), and vector representations for efficient data processing.

·      Implement and optimize GenAI models for performance, scalability, and efficiency, considering factors like chunking strategies for large datasets and efficient memory management.

·      Integrate GenAI models, including LLMs, into production pipelines, applications, existing analytical solutions, and RAG workflows, ensuring seamless data flow and information exchange.

·      Develop user-facing interfaces (UIs) using modern front-end frameworks (e.g., React, Angular) to deliver an intuitive and interactive experience for RAG applications.

·      Develop robust APIs (RESTful or GraphQL) using back-end frameworks (e.g., Django, Node.js) to facilitate communication between the front-end UI, GenAI models, and data sources.

·      Utilize LangChain and similar tools (e.g., PromptChain) to facilitate efficient data retrieval, processing, and prompt engineering for LLM fine-tuning within RAG applications.

·      Apply software engineering principles to develop secure, scalable, maintainable, and production-ready GenAI applications.

·      Build and deploy GenAI applications on cloud platforms (AWS, Azure, or GCP), leveraging containerization technologies (Docker, Kubernetes) for efficient resource management.

·      Integrate GenAI applications with other applications, tools, and analytical solutions (including dashboards and reporting tools) to create a cohesive user experience and workflow within the RAG ecosystem.

·      Continuously evaluate and improve GenAI models, applications, and user interfaces based on data, feedback, user needs, and RAG application performance metrics.

·      Stay up-to-date with the latest advancements in GenAI research, development, front-end and back-end development practices, integration tools, LLM architectures, and RAG functionalities.

·      Document code, models, processes, UI/UX design choices, and RAG application design for future reference and knowledge sharing.

Technical skills requirements

The candidate must demonstrate proficiency in,

·      Strong understanding of machine learning and deep learning concepts

·      Proficiency in Python (libraries like TensorFlow, PyTorch) with experience in vector data manipulation libraries

·      Experience with generative AI models (transformers, GANs, VAEs) and various LLM architectures

·      Experience with front-end development frameworks (e.g., React, Angular) and UI/UX design principles

·      Experience with back-end development frameworks (e.g., Django, Flask) and API development (RESTful or GraphQL)

·      Experience with NLP techniques (text cleaning, pre-processing, text analysis)

·      Experience with software engineering principles and best practices (object-oriented programming, design patterns, testing)

·      Familiarity with cloud platforms (AWS, Azure, or GCP)

·      Knowledge of containerization technologies (Docker, Kubernetes)

·      Experience with data integration tools and techniques (a plus)

·      Knowledge of chunking strategies for handling large datasets

·      Experience working with RAG applications and their functionalities

·      Experience in utilizing LangChain, LangGraph, and other agentic framework tools (e.g., AutoGen, Crew.ai) to facilitate efficient data retrieval, processing, prompt engineering, and multi-step reasoning within RAG applications. Experience building and deploying autonomous agents for specific tasks within the RAG ecosystem is highly desirable

·      Experience with DevOps principles and tools for continuous integration and delivery (CI/CD)

·     Experience with building and integrating with analytical dashboards and reporting tools

Nice-to-have skills

·      Experience working with RAG applications

·      Experience with cloud-based data warehousing solutions (e.g., BigQuery, Redshift, Snowflake)

·      Experience with cloud-based workflow orchestration tools (e.g., Airflow, Prefect)

·      Familiarity with Kubernetes (K8S) is a welcome addition

·      Google Cloud certification

·      Unix or Shell scripting

Qualifications

• B.Tech., M.Tech. or MCA degree from a reputed university