Sardar Zandieh

AWS Architectural Resilience Day comes to New York City! Please join me and other AWS resilience experts for a day full of informative talks and hands-on sessions that can help you build stronger and better in the AWS Cloud! #sre #devops #resilience

18

Did you implement Databricks over two years ago and are yet to migrate to Unity Catalog? A feature announcement that went under the radar recently is the ability to federate to an existing Hive Metastore (i.e. the original "data catalog" from older Databricks deployments) from Unity Catalog. This considerably lowers the onramp for Unity Catalog migrations and unlocks the ability to: 🔀 Capture data lineage 🔒 Enforce access policies 🔍 Increase observability on Hive Metastore assets. If migrating to Unity Catalog is one of your New Year's Resolutions, this is a great first step!

18

For those of you who were at the Boston Azure "Season of AI" event last night, I've posted the resources and info about my Semantic Kernel demo code with some additional resource links. DM me if you have any questions.

13

Although big and chunky cloud MPP databases are cool, I've always been a fan of open-source, compact, no-dependencies software, where vibrant community support and genuine love for product (and users) allow it to thrive among many commercial counterparts. #SQLite is great, so is #PostgreSQL, and now #DuckDB is emerging as the "hummingbird" of OLAP databases - small, fast and easy to manage. While it’s not (yet) as mature or feature-rich as some entrenched incumbents, it has already shown an immense potential for middleware-type workloads, where speed, #SQL expressiveness and interoperability are key. "AWS S3 data ingestion and augmentation patterns using DuckDB and Python" @

6

1 Comment

NYC's Office of Technology and Innovation (OTI) successfully modernized 29 critical city applications by migrating from legacy on-premises systems to AWS cloud infrastructure. The 18-month project, completed in April 2023, delivered enhanced security, improved uptime, and reduced operating costs while eliminating the need for 24/7 monitoring. Following this transformation, OTI launched MyCity, a unified portal for resident services, setting a new standard for digital government innovation in service delivery.

13

5 Comments

Curious about how to seamlessly integrate your cloud database using **Azure** and Oracle in a **Multicloud environment**? Wondering what the essential prerequisites are? Dive into the details with my newly crafted visual guide and master the art of Multicloud management! #CloudComputing #Azure #Oracle #OracleCloud #MicrosoftAzure #Multicloud #CloudTechnology #CloudSolutions #DatabaseManagement #ITManagement #TechInnovation #DataScience #ITProfessionals #CloudSecurity #EnterpriseSolutions #TechnologyLeadership #TechTrends #DigitalTransformation #TechCommunity #DevOps

5

In 2025, observability and security will converge like never before. Continuous compliance is just the beginning. See how, here.

1

AWS re:Invent 2024 delivered groundbreaking announcements with significant implications for cloud adoption in the public sector. Here's my perspective as a Chief Architect at Accenture Federal Services: Generative AI Takes Center Stage Amazon Bedrock: Enhanced features like model distillation enable agencies to deploy powerful AI solutions even with limited resources or strict security requirements. Bedrock's focus on data security and privacy is crucial for compliance with federal regulations. Amazon Nova: These new foundation models can revolutionize how agencies process and understand data, opening doors for innovation in areas like natural language processing and synthetic data generation. Trainium2 UltraServers: These servers accelerate complex AI workloads while adhering to stringent security and compliance standards, enhancing the performance of mission-critical applications. Compute Gets a Performance Boost Amazon EC2 Trn2 Instances: These instances offer attractive price-performance benefits for budget-conscious agencies. Thorough evaluation of their security posture is crucial before widespread adoption. AWS Trainium3: This signals AWS's commitment to purpose-built AI acceleration, ensuring federal agencies have continued access to cutting-edge technology. Amazon EC2 P5en Instances: With high bandwidth and networking capabilities, these instances are ideal for demanding federal workloads like high-performance computing. Integration with AWS GovCloud (US) will be key for supporting sensitive applications. Storage and Database Advancements Amazon S3 Innovations: New features like S3 Tables and S3 Metadata offer valuable tools for data management. Implementation must align with federal requirements for data governance and compliance. Amazon Aurora DSQL: This capability offers possibilities for modernizing legacy applications by bridging the gap between relational and document data. Looking Ahead re:Invent 2024 showcased the transformative potential of cloud computing for the public sector. Accenture Federal Services is committed to helping our clients navigate this landscape and leverage these innovations to achieve their mission objectives. https://lnkd.in/eF6jTVsg #AWS #reInvent #GenerativeAI #CloudComputing #FedGov #Innovation #AccentureFederalServices

75

1 Comment

I just got back from the Gartner IT Symposium, and a recurring theme in conversations with peers was the tension between agility and standardization in our 'agile' world. There’s a perception that standardization, frameworks, and processes can stifle creativity and innovation for engineers—a friction I’ve encountered often. But it took me back to my time in the Rangers, training alongside SEALs and Delta in joint operations. These units are some of the most disciplined, standardized, and highly trained individuals. Yet, they embody true agility and innovation, operating with unmatched flexibility within strict frameworks. This has me thinking: how can we adopt a similar mindset in Technology? How can we empower innovation within structure rather than seeing the two as opposing forces? There's something here, and I’ll be reflecting on it more.

42

3 Comments

Data discovery with #microsoft GraphRAG Microsoft open-sourced GraphRAG, extracting deep insights from unstructured datasets using LLMs. The GraphRAG use knowledge graphs to extract information and answer questions, so exiting More info: https://lnkd.in/gnt7wXv9 #microsoft #graph #graphRAG #dataAI

3

Mixture-of-Agents (MoA) methodology is a new approach that leverages the collective strengths of multiple LLMs. In this is construct a layered MoA architecture wherein each layer comprises multiple LLM agents. Each agent takes all the outputs from agents in the previous layer as auxiliary information in generating its response. MoA models achieves state-of-art performance on AlpacaEval 2.0, MT-Bench and FLASK, surpassing GPT-4 Omni. For example, our MoA using only open-source LLMs is the leader of AlpacaEval 2.0 by a substantial gap, achieving a score of 65.1% compared to 57.5% by GPT-4 Omni. Paper details here: https://lnkd.in/d6eAmtww

5

Things we don't talk about enough: 1) Adopting security to an agile workflow 2) Securing micro-services architecture 3) Letting the SWE roadmap guide your AppSec strategy What else?

13

10 Comments

Great insights as always by Jeff Winter! It is so important to make sure we are improving consistently so we don't get to the stage we NEED to. #SupplyChains are always evolving so just keeping up is the minimum that's needed, stagnation is no longer an option. Too many times I've seen people panicking about needing to "Do Something" because they haven't planned or implemented any form of change or improvement strategy! Stay ahead of the curve! #LetsTalkImprovement

2