Divya Ramesha

LLM is now capable of generating large JSON objects! 🚀 LLMs often need help generating or modifying large JSON blobs, leading to errors and inefficiencies. The new LangChain project is solving this problem by using JSON Patch operations and working on small parts at a time. If you're working with LLMs and need a reliable way to handle JSON data, I highly recommend checking it out: https://lnkd.in/gyTTe-DU

10

AlloyDB provides 2x better price-performance than self-managed PostgreSQL. See how in this article from Sridhar Ranganathan and Shesh Ranganath.

14

🚀 Exciting Opportunity Alert 🚀 Are you a Principal Engineer passionate about Distributed Machine Learning? Check out this role in Santa Clara, CA: https://bit.ly/3Zl5M4O. Key skills: #gpu #apache #spark #machinelearing #ml #dl #deeplearning #acceleratedcomputing #cluster #rapids #mLlib #XGBoost #PyTorch #cuML #pytorch #tensorflow #apis #api #Kubernetes #YARN #Ray #C++ #Scala, #Python #nvtabiular #cuda #horovod #petastorm #dll. Interested? Reach out to [email protected] for more details. Opportunity awaits! 🌟 #engineering #machinelearning #distributedcomputing

3

Open Policy Agent (OPA) and Rego are powerful tools for implementing policy-as-code in Kubernetes and other environments. OPA is an open-source, general-purpose policy engine that enables unified, context-aware policy enforcement across the entire stack. In Kubernetes, it's often used for admission control and authorization. Rego is the high-level declarative language used to specify policy as code in OPA. It allows you to express complex policies in a concise and readable format. Here's how OPA and Rego work together in Kubernetes: 1. Integration with Kubernetes: OPA can be deployed as a admission controller webhook in Kubernetes. This allows it to intercept and evaluate requests to the Kubernetes API server before they are persisted. 2. Writing Policies: Policies are written in Rego and typically stored in ConfigMaps or as files in the OPA container. 3. Policy Enforcement: When a request is made to the Kubernetes API, it's sent to OPA for evaluation. OPA applies the Rego policies and returns an allow/deny decision. Gatekeeper is an open-source project that provides a more Kubernetes-native way to use OPA (Open Policy Agent) for policy enforcement. It extends Kubernetes with Custom Resource Definitions (CRDs) for defining and managing policies using Rego. Reference for implementing gatekeeper for enforcing labels:

6

https://lnkd.in/gFWsZBEM Keeping pace with LLVM: compatibility strategies

10

2 Comments

🌍 H1B Visa? Not a Necessity for Global Success! 🖥️ According to a recent statement by Union Minister Piyush Goyal, the long-standing #H1B visa issue is now a thing of the past. But here's the bigger picture: Is an H1B even required to build cutting-edge applications and services? At Skyy Tech Inc, based in Mumbai, we believe that everything can be done remotely with the right team. We offer top-notch resources, including skilled software engineers and designers, to turn your vision into reality—no matter where you are in the world! Here are some key benefits of partnering with us: ✅ Cost Efficiency: By outsourcing, you can significantly reduce overhead costs without compromising on quality. ✅ Time Zone Advantage: While your business is winding down for the day, we are just getting started! We use time zone differences to our advantage, ensuring that your tasks get completed around the clock. ✅ Expertise at Your Fingertips: From development to design, our team has the skills and experience to handle everything remotely, saving you the hassle of visa issues or relocating talent. ✅ Faster Turnaround: Issues in other parts of the world can be resolved quickly when they arise during our non-peak hours. Partnering with us means you can scale your business seamlessly without worrying about visa hurdles or geographical barriers. Check out this article for more insights on the changing landscape of global talent: https://lnkd.in/dC6GUTFG

2

Two facts: First: Jack and the Storefront team handle some of the most interesting problems at Recharge if you're into caching, synchronizing, and lots of data puzzles to solve. Second: I work with the team as Principal so we'd get to have some fun while we do the first part.

17

Very interesting post on Intuit's use of LLMs to manage K8s, via Aditya Kulkarni at InfoQ: "Intuit Engineering's Approach to Simplifying Kubernetes Management with AI" https://lnkd.in/eRN6_sAK

2

Google’s Future Without Chrome The U.S. Department of Justice’s (DOJ) recent recommendation for Google to divest its Chrome browser marks a pivotal moment in antitrust enforcement. Stemming from a ruling that Google has monopolized online search and advertising markets, this move aims to restore competition and address concerns about the company leveraging Chrome to fortify its search dominance. While some see this as a catalyst for innovation, others worry about its potential ripple effects on developers and consumers reliant on Google’s integrated ecosystem. Google's response reflects its resolve to protect its product ecosystem and global leadership in technology. This development is a reminder of the delicate balance between regulation and innovation in the tech industry. As professionals, we should reflect on how structural changes like this could reshape market dynamics, encourage competition, and influence user experiences. What are your thoughts on the broader implications for the tech sector? #Politico, #AlJazeera, #CBC #News #Google #Chrome

4

1 Comment

I got a badge for participating in Kong Inc. API Summit 2024, for creating a plugin to monitor the LLM usage, log Traces, evals, prompt management, and metrics to debug and improve your LLM application with Langfuse (YC W23) #Kong #API #LLM #AI #Plugin

71

4 Comments

I took the AWS AI practitioner beta exam last Sunday and for me, it was challenging for a foundational cert. I had to answer 85 multiple choice questions but probably 35 questions were not graded. Besides, It required skills in Machine Learning, AWS Sagemaker, Responsible AI principles, and an overall understanding of AWS bedrock, including basic knowledge of how LLM's and foundational models work. A special thanks to Arturo Deza for the AI and ML concepts review at his classes, Harry Guillermo for motivating me to get into the AI field with AWS and Stéphane Maarek for his incredible course!!! #AWS #AI #MachineLearning #Sagemaker #ResponsibleAI #AWSBedrock #LLM https://lnkd.in/eQQtYJgz

44

1 Comment

I'm thrilled to see Amazon Q generally available. Amazon Q has revolutionized my work with Amazon Connect (contact center technology), empowering me to effortlessly build a sophisticated agent assistant and seamlessly integrate it with the Bedrock database, enabling powerful Retreive-Augment-Generate (RAG) Generative AI use cases. This powerful tool has not only simplified complex integrations but also enhanced efficiency. Additionally, I use Amazon Q as a personal assistant during my whiteboarding sessions, providing instant answers and insights about AWS Cloud services. The ease of use and robust capabilities of Amazon Q exemplify the pinnacle of modern technology, driving innovation and optimizing customer experiences. #TechInnovation #AWS

20

𝗠𝗶𝗹𝗹𝗲𝗻𝗻𝗶𝗮𝗹𝘀 𝗶𝗺𝗺𝗶𝗴𝗿𝗮𝗻𝘁𝘀 𝗳𝗿𝗼𝗺 𝗜𝗻𝗱𝗶𝗮 — 𝗬𝗼𝘂 𝗵𝗮𝘃𝗲 𝗮𝗻 𝗮𝗱𝘃𝗮𝗻𝘁𝗮𝗴𝗲 𝗶𝗻 𝘁𝗵𝗲 𝗴𝗿𝗲𝗲𝗻 𝗰𝗮𝗿𝗱 𝗽𝗿𝗼𝗰𝗲𝘀𝘀. 𝗔𝗿𝗲 𝘆𝗼𝘂 𝗺𝗮𝗸𝗶𝗻𝗴 𝘁𝗵𝗲 𝗺𝗼𝘀𝘁 𝗼𝗳 𝗶𝘁? Meet Pooja, a Product Lead who moved to the U.S. in 2008 for her master’s. After graduation, she landed her first job in Boston, but her initial employer didn’t file for her green card. She later switched to a Fortune 500 company, which filed her EB2 in 2012. Now, over a decade later, Pooja is still navigating the H1-B renewal cycle. Meanwhile, junior colleagues who arrived years after her are securing green cards through EB-1. Feeling stuck, she’s considering EB-1 herself but isn’t sure if the process is worth it. What Pooja doesn’t realize: ➡️ Her profile may already be EB1-worthy. ➡️ She likely meets the Critical Role and Salary criteria. ➡️ Her contributions, speaking engagements, and professional growth over the years all count. With a few targeted efforts, she could have an EB1-ready profile within a year, port her 2012 priority date, and get her green card in 12-18 months. Now, Pooja has two choices: Option 1: Take control with EB-1. Option 2: Hope the EB2 backlog advances and gamble on the wait. If you were Pooja, what would you choose? PS: If Option 1 feels like your path, consider joining our EB1 Slack Community(link in comments)! Every month, we help at-least five people accelerate their EB1 journey with the right strategies and tools.

4

1 Comment

House Moves on Bills to Extend AI Export Controls: This is huge for those hiring and working in AI/ML and adjacent tech. Once this is passed, US employers will need to obtain a license before releasing controlled tech or data to H1B workers — employees will need to be a green card holder or a citizen to work on AI/ML, and hiring companies will need to do extra work for those who are on H1B. It is not a stretch to predict that some nationalities / ethnic names may be screened with higher strictness for these jobs too. Big implications given current tech compensation shifts with AI/ML being one of the only areas not seeing negative growth. For the bill, see link: https://lnkd.in/geVDmPXm For a summary of the bill, see tweet: https://lnkd.in/gCP5VurV

4

1 Comment

LEAP - Quickly Understanding a New Codebase In the latest clip from our LEAP (LLM Enhanced Agile Programming) series, I utilize AI tools to help us quickly understand a new codebase. Tackling legacy code or unfamiliar projects can be daunting, but AI assistance makes it a breeze! Key Topics: - AI-Powered Analysis: Using Cursor.sh to gain an immediate overview of the Gilded Rose Kata project. - Automated Insights: Generating summaries of primary functions, classes, and critical highlights without diving into the code manually. - Quality Rules: Exploring how specific rules like item degradations and exceptional cases are handled within the project. Why This Matters: - Skip the steep learning curve with AI-guided codebase exploration. - Enhance your ability to quickly onboard new projects and legacy systems. - Leverage AI to optimize your workflow and improve code comprehension. Unlock the power of AI to master any codebase! #AIXP #AI #SoftwareDevelopment #LEAP #Python #Agile #CodingWithAI #CursorSH #Developer #Software #Programming #Tech #Coder #Technology Artium

1

The future of app development is here. Redis Released is our one-day event for developers to connect with Redis experts, learn about our product roadmap, and hear from the world’s largest brands on how they’re building with our powerful real-time technology. Here’s what we’ll share: → Our Product Roadmap → The World of Redis → Faster GenAI Apps Next stops: London on September 12th and New York City on October 17th. See you there: https://redis.io/released/

40