Leads the team this role joins
In-house, owns the opening
Put the opening up
From your own Gmail and LinkedIn.
About the role
This is a full-time, backend-heavy full-stack role in Bengaluru, India for engineers with at least three years of production experience who want to ship features from API through to client screens. The team builds the agentic side of an AI assistant, covering the chat service, streaming, and an agent harness that runs tools and sandboxed execution.
What you’ll do
- Design and own APIs shared by web, mobile and desktop clients, covering sessions, conversations, streaming turns and artifacts.
- Model data and manage migrations, auth, RBAC, pagination and search.
- Stream LLM output, tool calls and agent events to clients over an event bus, handling reconnects and partial failures.
- Contribute to the agent harness, including tool and MCP integrations, sandboxed execution and file flows.
- Build features across Kotlin Multiplatform apps and the Next.js web app.
- Own production observability, on-call work and root cause analyses, and improve speed and cost with measured results.
What they’re looking for
- 3+ years for SDE 2 or 5+ years for SDE 3 running production backend services.
- Deep experience in at least one backend language, with Python preferred; Go, Kotlin/JVM or TypeScript/Node also considered.
- Solid API and data model design, including PostgreSQL schema design, migrations, indexing and transactions.
- Understanding of distributed systems, including queues, event streams, idempotency and retries.
- Production experience on Kubernetes or a similar platform, with real debugging of incidents.
- Shipped user-facing features on at least one client platform: Android, iOS, desktop or web.
- Willingness to learn the less familiar side of the stack and agent or LLM systems.
- Clear written communication for design docs, pull requests and root cause analyses.
Nice to have
- Experience with LLM APIs, including tool calling, streaming, prompt caching or evals.
- Work with MCP servers or clients, OAuth connectors or sandboxed code execution.
- Kotlin Multiplatform or Compose Multiplatform, or native Android or iOS.
- Real-time systems such as WebSockets, SSE, NATS, Kafka or Temporal.
- Go services, or measured performance and cost work.
- Open-source work or public writing.
What’s on offer
- Full-time position based in Bengaluru, Karnataka.
Skills
Questions about this role
Is this role remote?
The listing gives Bengaluru, Karnataka as the location and does not describe a remote arrangement.
How many years of experience do I need?
The role asks for 3+ years for SDE 2 or 5+ years for SDE 3.
What languages does the role use?
Python is preferred for the backend, with Go, Kotlin, TypeScript or Node also welcome, and clients use Kotlin Multiplatform and Next.js.