Roro

Building LLM applications is a different dimension of software engineering altogether. Having cut through the fluff around generative ai and worked on several real LLM applications, here are few things that we do at Roro and severely enjoy. ?? Eliminate. (if the task shouldn't require LLM) ?? Categorise & Strategise. ?? Unstructured data science. ?? Development of LLM applications using LangChain. ?? RAG systems using vector databases like Pinecone, FAISS and ChromaDB. ?? Simple Agents based on ReAct prompt. ?? Complex Agents and multi-agent systems using LangGraph and flow engineering. ?? Monitor and optimise using LangSmith. ——————————————— Different LLMs have different behaviour and target use-cases. Here are a few things we do to optimise (cost+performance) the use of LLMs. ?? Different models for different use-cases, even within the same project. ?? Low cost or local models (using Ollama) for simpler tasks. ?? Decide if a use case require an LLM to be fine-tuned. ?? Pandas and Seaborn to prepare dataset for fine-tuning. ?? Fine-tune LLMs using platforms like OpenAI, LlamaFactory, Unsloth, Gradient and HuggingFace. ?? Case-optimise latency-accuracy trade-off during fine-tuning through quantisation, LoRA and pruning. ——————————————— It’s a very exciting time to jump on the Generative AI bandwagon. If you have a thought or use case around your business, we’ll love to talk and brainstorm. Visit our updated website at?www.roro.io?and a get a quote for your Gen AI project. #llm #generativeai #ai #langchain #vectordatabase #rag

From attendees to exhibitors—we’re now on the other side, showcasing AI that thinks. Come meet us at AI Bharat Expo, ?? Booth C265 ?? Hall 3 ?? Bharat Mandapam, Pragati Maidan, Delhi ?? March 19th to 21st, 2025 See you there! Achin Kumar Vaibhav Khanna Alok Vaish Sohini Bhattacharya

Charged up and ready to roll! We're proud to be the development partners powering this next step in EV charging innovation, alongside the incredible ChargeBay USA team. From closed beta to public launch—it's just the beginning. ??

Let's go! ??

Want to improve your iOS app’s performance? Adarsh Ranjan breaks down efficient caching techniques—from simple dictionaries to advanced LRU caches. Learn why NSCache is the go-to choice. Read now: https://lnkd.in/g8reAvWq #iOSDevelopment #Caching #Swift

#NewHireAlert We are pleased to welcome Rudra Kumar who is joining us as a Software Engineer and will be contributing towards Advanced Python, FastAPI and Data Science. Scroll the post to get to know Rudra in his own words. #TeamRoro

Struggling with Swift error handling? Adarsh Ranjan breaks down Optionals, Tuples, Result enums, and why ????-??????-?????????? is the cleanest way to handle errors. Read the blog now - https://lnkd.in/gY8QsG4T #Swift #ErrorHandling #CodingTips

We're super excited for this. Mark your calendars!

#NewHireAlert Say hello to our newest team member and Senior AI Engineer Amit Sharma. Scroll the post to get a quick intro to Amit in his own words. Amit comes with deep experience working with full-stack ML/DL across Banking, Healthcare and FMCG. Welcome to the team, Amit! ??

#MeetTeamRoro Meet Himanshu Bansal - our backend engineer for Android! When he's not coding, you’ll find him cruising on his bike or cracking Rubik's cubes. Swipe the post to get to know Himanshu better. ?? #TeamRoro