About this role

We want AI engineers who ship to prod, not publish to arxiv.

If you've built something with LLMs that actually works—not a demo, not a notebook, something real—you'll fit right in. We're looking for engineers who've wrestled with memory management, nailed context persistence, and know why most AI agents forget everything after two turns. You'll build AI agents from Day 0. Memory thatually remembers. Context that doesn't collapse. RAG that retrieves what matters. Raise the bar. Ship fast. Let's build.

What You’ll Do

• Implement memory to our AI Agents, ensuring proper context management
• Apply retrieval-augmented generation (RAG) pipelines to integrate LLMs with real-time data and context.
• Apply advanced techniques in prompt engineering, transfer learning, and custom model training.
• Optimize model performance and cost across production environments.
• Work with tools like Hugging Face, LangChain, OpenAI APIs, and vector databases (FAISS, Pinecone, Weaviate).
• Deploy scalable models using cloud platforms like AWS, GCP, or Azure, and containerization tools like Docker and Kubernetes.
• Collaborate with global teams and researchers in a fast-paced, remote-first setup.

Must-haves

• 4+ years of experience in AI/ML with deep exposure to Generative AI and LLMs.
• Experience working in Memory Management, Context setting and RAG.
• 2-3 yrs of purely Backed SDE experience is a must for this role.
• Preferably from Tier 1 colleges with a background in CSE preferred.

Compensation: We offer a competitive salary with ESOPs

If you’re ready to bring your unique vision to life and drive products that make a difference, we’d love to hear from you.

Interested candidates can Apply here