Ravi Srinivas Ranganathan

GenAI, Transformers & Their Real-World Relevance Transformers, initially crafted for language translation, have silently evolved into the foundation of today's AI advancements. From decision making to content creation, their presence is ubiquitous. However, the true significance lies in the thoughtful application of this transformative power. GenAI has transcended beyond mere demonstrations and research. It is reshaping: - Customer experiences through personalized interactions - Operational strategies via intelligent automation - Knowledge tasks with tools that enhance human cognition scalability The crux lies in harnessing intelligence for tangible outcomes - amplifying intuition, streamlining decision-making, and hastening insights. I'm intrigued to learn: What recent GenAI application has resonated with you the most? Secondly, How many technologies do you know that ended up revolutionizing far beyond their original purpose? #GenAI #Transformers #AppliedAI #EngineeringLeadership #Innovation #ThinkBig #HVSays

15

From Mid-Scale Hustle to Big-Scale Systems — My Leadership Journey When I worked at a mid-sized company — McAfee (formerly Intel Security), life as an engineering leader looked very different. I owned the entire tech stack end-to-end for the Real Protect SDK, which powered both enterprise and consumer security products. Decisions were quick. If I had an idea, we could experiment and roll it out within days. The visibility was immediate — the team saw the impact directly, and customers felt it instantly. But there were trade-offs: scale was limited, resources were stretched, and reliability sometimes gave way to speed. I wore multiple hats — tech lead, architect, and often the “on-call fireman.” Fast forward to today at Amazon. The canvas is massive — whether rolling out Prime membership features or building a multi-tenant portal to enable supply chain services for 1P & 3P sellers. Systems serve millions of users globally, reliability is non-negotiable, and playbooks ensure consistency across teams. I learn from some of the brightest minds, and every design decision forces me to think about scale, latency, and resilience. But here too, there are trade-offs: processes are heavier, decisions take longer, and ownership is often of just one slice of a much bigger puzzle. ⚡ What helped me move faster in this environment: Clarity of priorities → tie every discussion back to business + customer outcomes Cross-team relationships → build trust before you need alignment Document → Decide → Drive → cut endless meetings with written context & trade-offs Bias for small wins → ship incremental value instead of waiting for “big bang” launches Empowering the team → unblock quickly and let them own execution 💡 My takeaway: Mid-scale sharpened my ownership, versatility, and bias for action. Big-scale honed my systems thinking, discipline, and focus on reliability. The best leaders blend both — carrying startup agility into enterprise scale. 👉 If you’ve made the shift between mid and big companies, what was your biggest “surprise learning”? #EngineeringLeadership #TechLeadership #CareerGrowth #EngineeringManagement #ScalingTech #BigTech #StartUpCulture #LeadershipJourney

23

1 Comment

Ankur Goyal (CEO of Braintrust) told us something on the Data Neighbor Podcast that changed how I think about creativity in AI. He spent a month in a cave trying to make one AI feature work. Most of that month, he was pretty sad. Grind, grind, grind, grind, grind. Then suddenly it clicks. The people who look the most creative in AI? They just ran more experiments than everyone else. What you see as a breakthrough is the one attempt that worked after hundreds that didn't. He pointed at OpenAI as an example. Their perpetual optimism looked naive at first. But that optimism paired with relentless tenacity is what produced the things everyone now calls genius. "Maybe in the future, former athletes will be the best AI engineers." Athletes already know this. You show up, do the reps, and most days nothing visibly changes. Then one day it all snaps into place. If you're building with AI and feeling stuck, that's probably the right place to be.

37

4 Comments

Netflix CEO Ted Sarandos recently said something that sparked a wave of opinions. If I did it again, maybe we should have gone more "populist" instead of launching with Sacred Games. That one line set off reactions across the creative community. Anurag Kashyap, one of the directors of Sacred Games, responded bluntly saying "they should have started with Saas Bahu" 😄. And it made me pause. With my experience in product and leadership for two decades, I kept thinking, what can we, as leaders, learn from this? Because this is not just about a show. It is about the "bigger calls" we take when we enter a new market or shape a new vision. And sometimes, we look back and question our boldest bets. But let us rewind. When Netflix launched in India with Sacred Games, it did something brave. Sacred Games was not perfect. But it was fearless, gritty, and cinematic. And it marked a turning point for Indian OTT storytelling. The problem was not the launch. The problem was the lack of a strong second wave of equally good content. 💪 And if I were to rethink things as a leader aiming for sustainable growth, I would start by restructuring and re-evaluating the content curation team. This middle layer is broken, especially for many big OTTs in India, where content acquisition favors familiar faces over compelling stories. As a result, we got shows with huge budgets but low soul. High-star, low-substance titles like Murder Mubarak or Dabba Cartel, The Royals etc. But in the shadows, hundreds of incredible indie films and series never saw the light of day. Why? Because someone from Content Curation Room did not want to take a bet. 🙈 So I think Netflix and many other OTTs right now is lacking in evaluating their product from cultural-fitness perspective. And here is what I think as a product and tech leader: * Sacred Games was never the problem, treating culture as an afterthought was * Focusing only on scale, and not on depth Was Netflix did not need a more populist launch. It needed more Sacred Games, again and again. More bets that trusted voice over volume. And that brings me to leadership. When you take a bold call, you will not always get immediate applause. But leadership is not just about vision and strategy. It is about standing by the uncomfortable choices when others doubt them. And knowing that some decisions are about what you want to stand for, not just what returns the quickest numbers. If anything, the Sacred Games episode is a reminder that long-term brand value is not built by being safe. It is built by being right before everyone else agrees. What do you think? Are we too quick to question the bold moves? Is culture-market fit still underrated in global strategy? Would love to hear from leaders PS: I always meant Sacred Games Season 1 when I mentioned Sacred Games 😄 #Leadership #CultureMarketFit #ProductMarketFit #OTTIndia #Netflix #SacredGames #ContentCuration #BoldDecisions #StrategyAndExecution #BuildingForIndia

23

3 Comments

Last month, we were building an AI agent for a client. It was giving close to 50 percent wrong answers in long chats. After fixing the context setup and memory flow, the mistake rate came down to under 5 percent. So what was the real problem? Problems we found • The session was not keeping the right parts of the chat • Key user info was lost after every turn • No process to store facts from past steps • No method to clean long chat history • The agent was pulling the wrong details into the model • No rule to update old info when new info came in What we fixed • A clean session flow with the right structure • Compact history so the model reads only the useful parts • A stable memory layer to store past facts • A simple way to extract important info from each turn • A clear rule to update old info and remove noise • A setup for safe and correct retrieval before each turn These changes made the agent stable, clear, and consistent in every long chat. If you want to learn how to set up context and memory in the right way, this new Google guide on Context Engineering, Sessions, and Memory is very useful. Repost so more builders can learn from this. Save it for later. Follow Shubham Vora for simple and real AI agent insights.

78

46 Comments

ACTORS + AI: Director/Actor/Producer/Writer AI Chef 🧑‍🍳 Hans Obma visits the Cozy AI Kitchen 🎂 https://lnkd.in/gjiAvEfP to share his insights on how AI has transformed his creative processes. You may have seen Chef Hans in such 📺 hits as Better Call Saul, Wandavision, or Narcos — and yes, he's probably the most handsome AI 🧑‍🍳 chef we've had in the kitchen to date :-). Hans needed to learn a new language ... how did he do it? He got multimodal AI models to help him speak Welsh. Hans needed a way to scale how he communicated with his stakeholders ... how did he do it? He created an authentic-to-him way of scaling by creating an instant entourage of supporting agents. HT 🧑‍🍳 Ross Heise 🧑‍🍳 Matt Scholz and the power of the Wisconsin network for bringing such a storied talent to the Cozy AI Kitchen! --- This 🍰 episode: https://lnkd.in/gjiAvEfP All 50 episodes: https://lnkd.in/g6upvbGX

89

11 Comments

💡 AdTech Observations + Big News from Meta As someone who’s spent years working in the AdTech space, I’ve often wondered: Why hasn’t Meta tapped into WhatsApp for ad monetization yet? To me, it always felt like the next logical move — especially given WhatsApp's global user base and engagement rates. 🚨 Well, it’s official now — ads are coming to WhatsApp Status. To clarify: * No, you won’t see ads in your chat threads. * Yes, you’ll start seeing ads after viewing a few Status updates — similar to how it works with Instagram Stories. This move raises interesting questions about: * How users will react to a shift in WhatsApp’s traditionally ad-free experience * What this means for advertisers and creators looking to diversify their reach * And how Meta will balance monetization with user trust on a privacy-first platform What makes this development even more interesting: ✅ Untapped Market Potential:
WhatsApp has over 2 billion users globally — but it’s been largely untouched in terms of direct advertising. This opens up an entirely new inventory for advertisers, especially in regions like India, Brazil, and Southeast Asia where WhatsApp is dominant. ✅ Contextual Relevance:
Ads on Status could be more context-aware and native if Meta leverages user behavior across its platforms (Instagram/Facebook). It’s a playground for hyper-personalized targeting — without feeling overly intrusive. ✅ Cross-platform Ad Strategy:
This creates more synergy between Meta platforms. Think of it like this: One campaign can now run across Instagram Stories, Facebook Reels, and WhatsApp Status — giving marketers broader reach with a consistent creative format.

17

1 Comment

I recently found myself exploring about an interesting AI system design question: If Sanskrit and English had equal amounts of digital content available to train large language models (LLMs), would Sanskrit be the better language because of its well-defined grammar and logical structure? Sanskrit is often praised for its systematic grammar, explicit case markings, and structured sentence construction, where grammatical roles like subject and object are clearly encoded in word endings rather than inferred from word order. Intuitively, that feels like it should make reasoning easier for AI systems. However, modern LLMs are not rule-based systems that “apply grammar” the way humans learn it — they are statistical models that learn patterns from massive data. English, despite its ambiguities and looser structure, has simpler morphology and fewer surface variations per word, which aligns well with today’s Transformer-based architectures and tokenization methods. Sanskrit’s rich inflections and combinatorial forms, while logically elegant, can increase modeling complexity unless the architecture is designed to leverage that structure explicitly. This leads to a deeper realization: language structure alone doesn’t determine AI capability — architecture design and representation strategy matter just as much. It also raises a bigger question for the future of AI: as we move toward neuro-symbolic and reasoning-focused systems, could structurally explicit languages offer new advantages?

22

2 Comments

I am a Sr. Engineer and AI helps me create 5x more speed and value at Nielsen. I see a lot of these vibecoding memes. I love them, honestly, but jokes apart, if you figure out how to use AI right, it becomes very hard not to stand out in your org. And I am not talking about shortcuts. I do not go to Claude and say “refactor this entire feature and make no mistakes.” That is a good way to ship a bug factory. Here is what actually works for me. 1. Use AI to ask better questions. When I am working on a feature, I do not just say “write a service.” I ask: ➤ What are the edge cases I am missing ➤ What happens if this dependency fails ➤ What other design options do I have Forcing the model to explain the why behind each step sharpens my own thinking. 2. Use it to map end-to-end flows For big changes, I describe the full pipeline and ask it to lay out the sequence ➤ Ingest ➤ Transform ➤ Store ➤ Serve It helps me see where I am missing validation, logs, or access checks. Then I adjust the design myself. 3. Offload documentation After I finish the implementation, I let AI draft ➤ Function level comments ➤ High level design notes ➤ Release notes for the team I still review and edit, but it turns a painful task into a 10 minute job and my future self thanks me. 4. Plug it into the ML and analytics side I also use AI models as part of other pipelines to improve accuracy and signal. My job is to understand how those models behave, how to evaluate them, and where to place them so they help rather than confuse downstream systems. The pattern in all of this is simple. AI is not the engineer. It is the multiplier. If your fundamentals are solid and you keep asking why at every step, AI will make you much faster and much more reliable. If you skip the thinking and only ask it to “do my work”, you will look productive for a few weeks and then spend months debugging what you do not understand.

469

26 Comments