Vector Search & LLM Specialist

Location: Bangalore
Experience: 4-6 years

Notice Period: Immediate to 30 Days

About the Role

Hey there! We’re looking for an AI Architect who’s passionate about building cutting-edge generative AI systems with a focus on Retrieval-Augmented Generation (RAG). If you love making AI smarter by connecting it to real data and knowledge bases, this role is perfect for you!

What You’ll Do

As our AI Architect, you’ll be the brains behind our RAG systems, helping our AI provide accurate, contextual, and valuable responses by connecting large language models to our data sources. Some of your day-to-day responsibilities will include:

• Designing and implementing RAG architectures that combine the power of LLMs with our knowledge bases
• Optimizing vector search to make sure our AI finds the most relevant information quickly
• Managing vector databases and developing smart indexing strategies
• Creating and refining prompts that get the best results from models like GPT-4 and Claude
• Processing and managing large datasets to feed our hungry AI systems
• Fine-tuning and customizing models to better suit our specific needs
• Planning system integrations to make everything work together seamlessly
• Benchmarking performance and planning for scalability as our user base grows

What You’ll Need

You should be comfortable working with:

• Large Language Models from providers like OpenAI and Anthropic
• Vector databases such as Pinecone, Weaviate, or PGVector in Postgres
• Embedding models and techniques
• RAG frameworks like LangChain and LlamaIndex
• Vector search libraries including FAISS
• Deep learning frameworks such as PyTorch or TensorFlow
• Distributed computing for handling larger workloads

Why You’ll Love Working With Us

You’ll get to work at the cutting edge of AI, building systems that combine the power of the latest LLMs with the precision and reliability of knowledge retrieval. Your work will directly impact how our AI understands and responds to user needs, making it more helpful, accurate, and trustworthy.

If you’re excited about pushing the boundaries of what’s possible with RAG models and have 4-6 years of experience in this space, we’d love to chat with you!

Ready to build the future of AI? Apply now!