AI Engineer

Had an Amazing time at the AI Engineer World Fair, it was amazing to connect with everyone and see all the excitement of building new AI apps. Had fun time giving my hands on Workshop on building Generative AI apps on AWS and demoing the Model Brawl League.

Had a great time at AI Engineer World Fair last week. Here are some of my top highlights from this knowledge-packed event: 🌟 Favorite Talks🌟 1. A Practical Guide to Efficient AI by Shelby Heinecke, PhD, Senior AI Research Manager at Salesforce. Dr. Heinecke addressed the challenges of deploying AI models efficiently, how using small models like Lora and Qlora helps on reducing latency and resource consumption: Quantization Framework and comparison. Note! Don't assume that 4bit or lower is the answer; measure your model and evaluate the final model, especially for health and safety use. 2. Scaling AI in Education by Shawn Jansepar, Director of Engineering at Khan Academy The Talk covered Khan Academy's journey to becoming an AI-first organization, focusing on the AI Tutor, Khanmigo. I also learned how complex it is as different people have different learning patterns, and bringing specialized tutoring is a challenge indeed. 🌟 Best Learning Experiences🌟 1. Running AI Applications in Minutes: Quick Start with AI Templates by Gabriela de Queiroz and Pamela Fox Gabriela and Pamela demonstrated how to quickly deploy AI app templates using Azure OpenAI Proxy, including a simple OpenAI Chat App, a chat app using Retrieval-Augmented Generation (RAG). 2. Karthik Vangati giving me a personal lesson on what is Vector search and how MongoDB has been incorporating features that support it. 🌟Notable Companies Leading the Way🌟 DataStax - Empowering real-time AI applications with Astra DB, built on Apache Cassandra. Sri Bala further clarified how they support production-level AI by delivering accurate, real-time data results. OctoAI - Specializing in delivering efficient, reliable, and customizable AI systems. Anna Connolly helped me understand how OctoAi aims to transform the machine-learning lifecycle with innovative solutions. Sourcegraph - Enhancing code intelligence and collaboration for developers worldwide. Alex Isken presented how to customize your language models and can use them offline as well. neptune.ai - This platform tracks experiments, monitors training and ensures reproducibility, catering to commercial and research teams. Patrycja Jenkner informed us how it's helping data scientists and ML engineers streamline their workflows. The AI Engineer World's Fair 2024 was a great time. Thank you, everyone, for the education and knowledge experience!! #machinelearning #artificialintelligence #genai

Just got back from the AI Engineer World's Fair in SF, and wow, what a ride! 🚀 3 days, 2000 AI nerds, and more mind-blowing ideas than I could count. For once, I didn't have to explain what I do for a living – everyone just got it. The event was packed with insightful presentations, hands-on workshops, and cutting-edge demos that truly showcased the future of AI. Industry experts from Google, Perplexity, Discord, Tinder, and Zapier shared their experiences and insights into building AI products. Key takeaways that are still buzzing in my mind: 1. Evaluation is everything: What can't be measured, can't be optimized. 2. RAG (Retrieval-Augmented Generation) is more than just vector embeddings. Hybrid, modular, and graph retrievers (neo4j) are the new hotness for handling complex scenarios. 3. Inference speed is getting cheaper and faster. Startups like Fireworks AI, @Grokk are pushing the boundaries here. 4. Co-Pilots are here to stay. Companies across finance, legal, insurance, and storage are all trying to integrate co-pilots into existing applications. 5. Engineers with product sense will have an edge in this rapidly evolving field. But the real magic? Those unplanned hallway chats. I met startup founders, working on Agents/Memory/Inference, geeked out with industry counterparts about NL2SQL, Evals, Generative UI, and nearly missed a session brainstorming with a fellow hacker. Vinay Pinnaka Anil Krishna C. Matthew Ambrogi Eugene Yan Abhinav Gupta Patrick Debois John Knox Jayasimhan Masilamani The conference was a stark reminder that the field is moving at lightspeed, and it's clear that continuous learning is the name of the game. I will most definitely be back to soak in more of this vibrant atmosphere next year. Until then, I am looking forward to applying the insights I picked up this year. https://lnkd.in/ge5A5eXS #AIWorldFair #SFTech

Our general partner Brittany Walker recently joined 2,000 software engineers enhanced by, and building with, AI during the AI Engineer World's Fair. You can check out the replay of her hosting the CodeGen track at the 2:30:14 mark here. #PowerToTheMakers #CodeGen #AI #artificialintelligence https://lnkd.in/g_EuHuQx

The Future of Knowledge Assistants 🤖 At the AI Engineer World Fair, we covered what it means to build a better knowledge assistant beyond using naive RAG. There are three main components: 1️⃣ Advanced data and retrieval modules: Have an advanced set of capabilities for parsing, chunking, and retrieval even before you try out fancier orchestration techniques. 2️⃣ Advanced single-agent query flows: Treat all data interfaces as tools, use agentic reasoning to build personalized QA systems. 3️⃣ General multi-agent task solvers: Build a multi-agent system as event-driven microservices in order to better collectively solve a task, whether through an agentic orchestrator or through an explicitly defined orchestrator. Along the way we released some cool announcements: - Llama-agents + a sneak peek into our LlamaCloud waitlist Slides: https://lnkd.in/gkQikWJG llama-agents: https://lnkd.in/g37FkPyx

Came out of the AI Engineer World Fair last week alongside Gabriel Jai representing FutureFit AI, held in the heart of Silicon Valley. We divided and conquered across sessions with him taking the technical tracks and I jumping into the AI Leadership track. A couple of themes stood out across sessions: 🤖 Agentic Workflows: Autonomous agents get the hype, but building "agentic workflows" closely contextualized to a domain is where the real value is. "Chatbots are so 2023" was a common sentiment. 🔎 Evals, Metrics, & "Vibes": After over a year of AI frenzy, companies are hungry to measure ROI on their investments. There are new tools that can do this better, but some is still more art than science. (Many vibes jokes were made.) 🎯 Product AI: Sessions held by companies like Khan Academy by Shawn Jansepar and Chegg Inc. by Yash Shah and Taranveer Singh went deep on their lessons learned in productizing AI, both highlighting the role that product leaders hold in leading AI-first product lines and driving adoption by focusing on solving real problems and user experience. 👩💻 Teams & Tasks: The role of the AI Engineer might be a new formality, but most roles involved in product development are expanding and shifting. Dev processes are likely to follow course. The real magic happens when pairing domain experts with the 10x builders. 🛠 Tools: The expo was full of new 1-2 year old AI eng suites products like 🔭 Galileo and OpenPipe aiding evaluation, prompt tracing, and experimentation. AI engineering is still largely experimental, and it's easy to get lost in the weeds without the right tooling. Lastly, AI Engineers are funny! Had a few laughs and am looking forward to tuning into sessions I missed online (all recorded).

last week, I gave a talk on designing good AI products at AI Engineer. I touch on what I learned from working on the Vision Pro at Apple, and working with + talking to hundreds of AI companies. you can watch the talk here: https://lnkd.in/gDX6NVUS High Level: 1. Start with What Matters 2. Focus on Hierarchy 3. Leverage Familiarity #AI #UX #ArtificialIntelligence #Product #PM

Introducing Hyperspace: A new frontier in decentralized AI. Built on @HyperspaceAI's community-powered network, it combines prompt engineering, visual react flow, Python execution, and web browsing capabilities

This week’s highlight: the Neo4j colleagues in this photo, others behind the scenes, and thousands of AI builders, leaders, innovators & educators bringing hands-on know-how to the biggest technical AI conference in SF with the AI Engineer World’s Fair. A big part of this was all about GraphRAG, the combination of knowledge graphs + RAG for LLMs that is essential for GenAI. Standing left to right: Theo Hopkinson, Jason Koo, Trevor Martel, MBA, Charles Dolan, Alison Cossette, Andreas Kollegger. On the floor: Michael Hunger, Nariné Tchintian, John Stegeman, Yolande Poirier and me. Below: Zachary Blumenfeld, Emil Eifrem, Philip Rathle & Alison. Forums like these set the pace for everything that follows, so all the better to share and learn what's happening at AI's forefront. Added thanks to Kidus Anteneh Adugna whose common caring on tech for good made meeting him memorable, Pagely Tucker for feeding my soul, and FPV Ventures' Christina L. for her spirit of discovery & generosity that naturally draws others to her -- and they should. #AIEWF #GraphRAG #knowledgegraphs

Groqsters had a great time meeting so many folks during AI Engineer World's Fair this week in San Francisco. Interesting sessions and good people with lots of great questions. AI educator Harper Carroll even stopped by and said hi to the team!