Xin Feng

Check out the latest in our "Debuggability" blog series! This blog is authored by Kevin Downey Jason Johl and me and talks about how we built a Debuggability Paved Road at Intuit using Ephemeral Containers and Argo Workflows. We'd love to hear your thoughts on the topic. Also, what tools do you build as-a-platform to help debug service, compute and network issues in Kubernetes at scale? #intuit #kubernetes #debug

23

Want a preview of what I'm going to be talking about in my keynote for RubyConf? You can catch a glimpse of it here!

10

If you're looking to learn about how Transformers "ate" all other architectures here's a great overview by Lucas Beyer from Google DeepMind. The slides are available at https://lnkd.in/gNpGhqPj. https://lnkd.in/guFtEp7i PS> I recommend watching 3Blue1Brown's intro to Neural Networks first if you've not caught up w/ his latest series: https://lnkd.in/gfU-Ccx5

158

3 Comments

Hey everyone, I am an investor and advisor to Katanemo.... They are reinventing the infrastructure primitives for GenAI and launched Arch - https://lnkd.in/gCrbbkEV - an intelligent prompt gateway. Give the project a look on Github, and star the project if it resonates

88

3 Comments

This is the upside of having a monorepo. Successes like this depend on being able to change code at scale safely and with clear understanding of performance impact. The changes themselves are done by a fairly small team, but the systems that enable us to continuously roll changes with critical company wide impact like this are key to make this possible.

38

9 Comments

What type of AI would be helpful? The accurate ones.

3

1 Comment

From my conversations, I'm noticing different trends between how AI engineers deploy evaluation models (model as a judge) in production monitoring vs application testing. 💡 Value - Monitoring: provides real time alerts of performance or used to preemptively block problematic outputs from surfacing to the user -Testing: regression testing applications to establish baseline performance before pushing to deployment ⚡ Speed - Monitoring: near real time, requires extremely fast token processing - Testing: batch, async, often processing large test sets, lower token processing speed required 🎯 Accuracy - Monitoring: overindex on false positives, better to flag something as problematic and be wrong than to let something slip between the cracks - Testing: high correlation with human graders, be as accurate and robust as possible 💰 Cost - Monitoring: prefer cheaper models, otherwise the additional inference cost per generation will add up exponentially - Testing: willing to take on higher costs, calculation is accurate testing leads to better performing outputs 🛑 Risk - Monitoring: if your monitoring judge gets something wrong, there is a high consequence because it directly impacts the end user - Testing: if your testing judge gets something wrong, async review gives some potential to remediate the issue At the moment, it seems using model as a judge for testing is a little more popular due to the high cost constraints of constant monitoring, but that is subject to change as more specialized models come out. As the industry matures, I strongly believe we're gonna see specialization between models for monitoring and models for testing. If you're currently using model as a judge techniques, would love to chat more! Let me know what you think. Twitter Handle: https://lnkd.in/eAsQvtiu

26

So excited to see our team's work featured here! These are fundamentals directions for recommender systems, essential for advancing the field. Excited to see how others will build on this and drive deeper insights. https://lnkd.in/gkqpq7HS

134

4 Comments

I am excited to share the latest blog, co-authored by myself, Junhwi Kim and Vyas Sekar, detailing how we managed to successfully localized and improved LLM by combining Fine-Tuning and RAG. https://lnkd.in/gKDkgGPq

70

3 Comments

LLMs and LangChain: The Dynamic Duo 🦸‍♀️🤖 Just finished a fun project where we built a Q&A bot using these two powerhouses. It's like having a personal AI assistant that's always ready to answer your burning questions! 🔥 Here's what I learned: LLMs are wizards: They can conjure up answers from thin air (or, uh, the internet). 🧙‍♂️ LangChain is the glue: It holds everything together and makes it easy to use. 🔗 Endless possibilities: This tech can be used for anything from customer support to writing catchy social media posts. 📝 Want to see it live (obvio a test server link 😛 ): https://lnkd.in/dZNAVCSV Note: it's a render link, they will take down the instance because of no use, you can hit the link and wait for two minutes, they will spin up the instance and you can try it out. Want to see the code? Check it out here: https://lnkd.in/dzjh4r47 #AI #MachineLearning #NLP #LangChain #LLM #Python #Developer #FunProject"

22

Building a Two-Tower Personalized Recommendation System Powered by GNNs, LLMs, and RL Excited to share an innovative Two-Tower Recommendation System that integrates Graph Neural Networks (GNNs), Large Language Models (LLMs), and Reinforcement Learning (RL) for personalized recommendations on Yelp business data! 🔍 Key Highlights: 1️⃣ GNNs for graph-based user and item embeddings. 2️⃣ LLMs (e.g., Sentence Transformers, GPT-2) for contextual understanding. 3️⃣ RL to optimize recommendations using Chain-of-Thoughts. 💡 Why It’s Exciting: This system blends graph intelligence with semantic reasoning and creates a robust framework for dynamic, user-focused recommendations. It’s a scalable, adaptable approach for advancing AI-driven personalization. #AI #ML #RecommendationSystems #GraphNeuralNetworks #LLMs #ReinforcementLearning #GenAI #LargeLanguageModels

48

4 Comments

🎉 Big congratulations to our incredible team (Haoyu Chen, Nick Greenquist,Yuxing Wang, Sridevi Maharaj, Ruiyang Wu and many more) for delivering several quarters-long impactful features on the Play Store! 🚀 We’re thrilled to have launched key updates like Search Home, Sports Moment, and WearOS recommendations, all designed to enhance personalization and help billions of users worldwide search and discover content they love. 🌍✨ Check out the Play Store Q3 updates: https://lnkd.in/dn5wx8Mi #GooglePlay #Personalization #Recommendation

74

1 Comment

I gave a talk on Protein folding and what it means for drug discovery at PyData London. I, like a lot of folks, have been interested in the developments of protein folding and thought it would be fun to have a go at folding a protein and then doing something with it like looking at on-target and off-target drug bindings for a well known receptor, the Beta-1 adrenergic receptor, which is important in stroke, coronary artery disease, and congestive heart failure. Activating the receptor increases your heart rate, and contractility and conversely blocking the receptor decreases your heart rate, and contractility. In the talk, I use open-source tools like RDKit, Biopython, PyMol, dockstring, Autodock Vina and AlphaFold to fold a protein (the Beta-1 Adrenoceptor) and then pose the drug propranolol to it and compared it to the endogenous agonist noradrenaline; "endogenous" means "made by the body", and "agonists" are chemicals that activate a particular receptor. I then compared this to another drug, simvastatin, to see how you could compare a drug that is known not to affect this receptor to demonstrate that while other drugs are energetically favourable to interact with this receptor that it doesn't interfere with where the agonist binds. I'm hoping that this talk will be useful to those in drug development that are interested in the applications of protein folding. It certainly gave me some ideas about how we could use these techniques to screen compounds in silico. YouTube: https://lnkd.in/eWZSu9TH GitHub: https://lnkd.in/ehvEJfjy #pydata #pydatalondon #pydatalondon2024 #alphafold #rdkit #pymol #drugdiscovery #drugdevelopment #insilico #pharma #pharmacology

37

3 Comments

I first joined Amazon in December of 2005. Even though I left for two years, my "Amaversary" still coincides with the end of the year and a natural moment for reflection. As I reached my 17 year mark this December, I also had the privilege of working with Amazon Careers to share some of my journey and thoughts about individual contributor technical leader and people manager career paths. In my ruminating, I put together far more content than could be used for a single article. So, I've decided to post here as a series of Q&As - in case others might find my observations, experiences, and perspectives interesting or useful. Below is the first of 6. 1. 𝘽𝙧𝙞𝙚𝙛𝙡𝙮 𝙨𝙝𝙖𝙧𝙚 𝙮𝙤𝙪𝙧 𝙘𝙖𝙧𝙚𝙚𝙧 𝙟𝙤𝙪𝙧𝙣𝙚𝙮; 𝙬𝙝𝙖𝙩 𝙢𝙤𝙩𝙞𝙫𝙖𝙩𝙚𝙙 𝙮𝙤𝙪 𝙩𝙤 𝙩𝙖𝙠𝙚 𝙤𝙣 𝙙𝙞𝙛𝙛𝙚𝙧𝙞𝙣𝙜 𝙘𝙖𝙧𝙚𝙚𝙧 𝙥𝙖𝙩𝙝𝙨, 𝙄𝘾 𝙫𝙨 𝙢𝙖𝙣𝙖𝙜𝙚𝙧? I started my career as a software engineer 25 years ago. I've worked for startups, enterprise companies, and 7 different organizations over 17 years and two tours at Amazon. I've written firmware for robotic camera mounts; built highly scalable distributed systems; designed restaurant marketing, ordering, logistics, and operations software; created automated test harnesses for mobile games; tested HD DVD encoding; helped launch grocery delivery to customers around the globe - just to name a few of the many cool things I've had the privilege to work on. I've been an entry-level software engineer, a technical lead of teams, a software manager on a couple of occasions, chief software architect reporting to a CTO, and (for the last few years) Amazon Principal Engineer directly supporting a VP with about 200 engineers within my remit. I first became a manager because I mistakenly thought it was the only way to continue growing as a leader, and in many ways I failed. I learned some very humbling lessons about leadership through that experience, which I used to be a better individual contributor technical leader on my path to Senior Engineer. My second time as manager was because my organization had a need that I could fill. I had grown enough as a leader that this time I was much more successful. I said yes to an opportunity that started with managing a small team through delivery of a complex and critical project. Once I grew a high performing team that delivered that initial project, I took on more scope and expanded into multiple teams. After a couple of years of success growing and investing in my teams so that we could deliver greater value to our customers and business, I decided to prioritize being close to my family. For me, at that time, it meant giving up my people management role and returning to the role of an individual contributor technical leader that supports a globally distributed organization. Even though I really enjoyed my time as a people manager, there is no better job for me than that of a Principal Engineer. #amazon #careerdevelopment #technicalleadership #peoplemanagement

91

3 Comments

Munir Al - Dajani and I wrote about our overall approach for aligning GPT to a healthcare task - check it out! We're also planning some more in-depth & more technical blogs for the near future so stay tuned.

19

The future is here

5