Company Overview

Sarvam AI is a pioneering generative AI startup headquartered in Bengaluru, India. We are dedicated to leading transformative research and development in the field of language technologies. With a focus on building scalable and efficient large language models (LLMs) that support a wide range of languages with a particular emphasis on Indic languages, Sarvam.ai aims to reimagine human-computer interaction and build novel solutions.

Role Overview

As a GenAI app developer for android & iOS, you would be aligned with the Edge AI vertical that is working on building AI models for on-device deployment on smartphones. Your role would include developing minimalistic Android and iOS apps to showcase our on-device models, integrating various speech & text AI models with the app, and working on optimisations for enhancing inference latency and compute resource utilisation. We will start these apps with Android, but eventually also develop them for iOS

Key Responsibilities

• Develop Android applications with FE, BE and API integrations (Plus if you can also develop iOS apps)

• Understand various LLM architectures and implement optimisation techniques to deploy these models on-device

• Collaborate with the Models and Infrastructure team to relay requirements for efficient integration with the Android SDK

• Work on model optimisations to ensure inference latency on-device is low

• Work on ensuring compute resource utilisation (GPU/NPU) is efficient and doesnt affect other smartphone processes
  

Requirements for the Role

• Bachelor's degree in Computer Science, Engineering, or related field

• Experience with developing LLM-based e2e Android applications

• Familiarity with prompt engineering

• Experience of working with Open Source SLMs like Llama 1B, PHI-4-mini, Qwen 1.5B etc (Bonus if you have deployed them locally and done inference optimisations)

• Proficiency in Python, Kotlin, Java

What we Offer

• Exposure to building foundational models from scratch and optimising them for devices

• Competitive salary

• Hybrid work from office flexibility

• Health insurance and other benefits

• Exposure to industry-leading partners in the Hardware space for model optimisations