GenAI Architect

The GenAI Architect role is a hands-on position requiring deep technical skills and expertise in implementing enterprise applications using SQL and unstructured data (e.g., images, videos, logs). The role involves working with Autogen, CrewAI, Azure OpenAI GPT-4 Turbo, and GPT-4V. The primary responsibility is to design and develop complex AI applications that render insights from data through NLP-based prompts, focusing on architectural design and performance optimization.

Responsibilities

1. Collaboration. Work with stakeholders to understand business needs and translate them into architectural blueprints.
2. Design. Create scalable, secure, and high-performance architecture for Autogen-based LLM-integrated applications.
3. Data Models. Define data models and schemas to integrate operational data from relational databases.
4. Leadership. Lead implementation efforts, ensuring adherence to architectural guidelines and best practices.
5. API Development. Develop APIs and interfaces for seamless communication between applications and databases.
6. Code Quality. Write efficient, maintainable code following coding standards and version control processes.
7. Data Integration. Integrate data from relational databases into the application, ensuring consistency and integrity.
8. Testing. Conduct thorough testing, including unit, integration, and performance testing, to validate functionality and scalability.
9. Troubleshooting. Debug issues arising during integration and testing phases.
10. Performance. Identify and address performance bottlenecks and optimization opportunities.
11. Tuning. Implement strategies to improve speed, reliability, and efficiency of data retrieval and processing.
12. Monitoring. Continuously monitor system performance and proactively address inefficiencies.
13. Documentation. Create comprehensive technical documentation, including architecture diagrams, API specs, and deployment procedures.
14. Knowledge Sharing. Conduct sessions to share architectural knowledge and best practices with team members.
15. Mentorship. Provide guidance and mentorship to junior team members.

Requirements

1. Frameworks and Tools. Expertise in Autogen Framework, CrewAI, WrenAi, SQL Agents, AG-Grid, Flask/Django/FastAPI.
2. Core Python Skills. Proficiency in Core Python, including iterators, generators, OOP concepts, Python Shell, and ORM.
3. AI and Data Handling. Experience with AI search, vector database creation for relational and unstructured data, Azure AI services.
4. Azure Expertise. Deep knowledge of Azure SQL, Azure Data Factory, Linked Services, Azure Synapse, and cloud app services.
5. Experience. 9-10 years in core application development with at least 3 years in AI project architectural leadership.
6. Python Frameworks. 5+ years leading development of AI applications using Python backend frameworks and inferencing pipelines.
7. Prototyping. Skills in rapid PoC/prototyping and building application blueprints independently.
8. Technical Proficiency. Hands-on expertise in Python, AG-Grid, ReactJS, SharePoint indexes, and data structures.
9. AI Technologies. Familiarity with Azure Form Recognizer, TaskWeaver, Autogen, Agentic Flows, RAG, RLHF, and vector databases like Pinecone, FAISS, Weaviate, ChromaDB.
10. NLP Techniques. Knowledge of NLP techniques such as transformer networks, embeddings, and intent recognition.
11. MLOPS/LLMOPS. Skills in embedding and fine-tuning Azure OpenAI models using MLOPS/LLMOPS pipelines.
12. Communication. Strong communication, architectural sketching, and collaboration skills.

This position is ideal for experienced AI architects who are adept at designing and implementing complex AI applications, particularly in the context of large-scale operational databases and advanced AI frameworks.