Overall Objectives of Job: (If multiple sections, accord weightage to each section)
•    The primary objective of this role is to design, develop, and maintain robust backend services and APIs for Generative AI-enabled applications. The role involves integrating advanced generative AI models into scalable and secure applications, ensuring efficient data management, and leveraging cutting-edge RAG techniques to enhance the accuracy and relevance of AI-driven responses. The role requires a strong foundation in Python programming, backend frameworks, and cloud services, along with hands-on experience in data ingestion, ETL processes, and database management. The individual will work collaboratively with cross-functional teams to deliver innovative AI solutions that meet the evolving needs of the business and its stakeholders.    

Duties and Responsibilities
List in order of importance and state approximate weightage accorded to each.

•    Develop and maintain backend services for GenAI enabled applications
•    Create APIs for frontend integration for GenAI applications
•    Ensure secure data storage and retrieval
•    Integrate Generative AI large language models into applications
•    Ensure the right approach for Retrieval Augmented Generation and achieve accuracy of responses for different use cases
•    Develop data ingestion pipelines for different data sources such as confluence, sharepoint, JIRA etc,
•    Ensure efficient data storage and retrieval
•    Maintain data quality and integrity

Qualification, Experience, Technical and Functional Skills

•    Bachelor's degree in Computer Science, Information Technology, or related field.
•    Minimum 5 years of experience in software development, with a focus on backend services and API development.
•    Proven experience in developing and maintaining backend services for Generative AI-enabled applications.
•    Hands-on experience with generative AI frameworks such as Langchain, LlamaIndex, etc.
•    Experience with backend frameworks such as Django and Flask.
•    Proficiency in Python programming language, along with Generative AI frameworks such as Langchain, LlamaIndex, etc.
•    API development and integration for ML models
•    Database management (SQL, NoSQL) including vector databases such as Postgres, GraphDB (Neo4j)
•    Experience working with generative foundational AI models and using API endpoints from Azure/AWS to build applications on top of these foundational models for RAG, fine-tuning approaches
•    Strong hands-on experience in RAG techniques (chunking, embedding, and indexing), retrieval and synthesis, feedback loop mechanisms
•    Good hands-on experience with prompting techniques and creating prompt templates for specific use cases to set the right contexts
•    Experience with different cloud services (AWS, Azure) and use of cloud platforms for model augmentation, fine-tuning
•    Data ingestion and ETL processes
•    Database management (SQL, NoSQL)
•    Experience with data pipelines (Apache Kafka, Apache Spark)
•    At-least 3 years of working experience in Machine learning projects, 
•    Strong technology awareness (systems, technologies, development cycles) 
•    Experience in working in Agile (Scrum) methodology
 

Allianz Group is one of the most trusted insurance and asset management companies in the world. Caring for our employees, their ambitions, dreams and challenges, is what makes us a unique employer. Together we can build an environment where everyone feels empowered and has the confidence to explore, to grow and to shape a better future for our customers and the world around us. 
We at Allianz believe in a diverse and inclusive workforce and are proud to be an equal opportunity employer. We encourage you to bring your whole self to work, no matter where you are from, what you look like, who you love or what you believe in.
We therefore welcome applications regardless of ethnicity or cultural background, age, gender, nationality, religion, disability or sexual orientation.
Join us. Let's care for tomorrow.