- Design and ship high-quality Android applications for consumer and enterprise audiences, while leveraging AI/LLM tools to build intelligent product features and accelerate development workflows.

- Build and maintain robust Android applications using Kotlin, Jetpack Compose, and XML layouts.

- Own end-to-end feature delivery - from architecture and UI to API integration, testing, and release.

- Integrate cloud LLM APIs (OpenAI, Anthropic, Gemini, etc.) into mobile apps to power intelligent, user-facing features.

- Build internal AI-powered developer tools - code assistants, smart documentation helpers, automated testing aids, and similar workflow accelerators.

- Design lightweight prompt engineering solutions and manage LLM API call lifecycles - error handling, retries, latency, and cost-awareness on the client side.

- Collaborate with backend, QA, design, and product teams in a structured enterprise environment.

- Contribute to reusable internal components or SDKs that make LLM capabilities easier to leverage across the team.

Ideal Profile :

- 4 - 6 years of professional Android development with a portfolio of shipped consumer and/or enterprise applications.

- Hands-on experience integrating at least one AI-powered feature or developer tool into a real product or workflow.

- Strong understanding of Android performance, debugging, and release processes in a structured team environment.

- Practical knowledge of LLM concepts - prompts, context engineering, basic RAG, knowledge bases, and latency/cost tradeoffs.

- Familiarity with MCP and how it enables LLM-connected workflows.

- CI/CD experience, automated testing (unit + instrumentation), and comfort with enterprise-grade release processes.

Skills Required :

- Android Developer role demands strong mobile engineering as the foundation, augmented with practical AI/LLM integration experience

- Kotlin (must-have) : coroutines, flows, modern async patterns

- Jetpack Compose + XML layouts - hands-on with both

- Android architecture : MVVM, clean architecture, Jetpack components (ViewModel, StateFlow, Navigation, Room, WorkManager)

- Dependency injection - Hilt or Koin

- LLM API integration : calling and consuming OpenAI, Anthropic, Gemini or equivalent in production

- Prompt engineering basics : context management, token usage, cost tradeoffs

- RAG (Retrieval-Augmented Generation) : working knowledge of retrieval pipelines and when to apply them

- Knowledge base construction : familiarity with chunking, embedding, and indexing content for LLM consumption

- MCP (Model Context Protocol) - basic awareness of how tools, APIs, and data sources connect to LLM workflows