SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: IDR 35,000,000 - 45,000,000 / monthly
Kulu is building AI agents that join live meetings in real time—listening, speaking, seeing shared screens, and taking actions. The company is hiring a Platform Engineer to own the realtime infrastructure that powers this experience: WebRTC media infrastructure, streaming multimodal LLM sessions, Python backend services, and cloud deployment across AWS.
You'll report directly to the CTO and work alongside the Lead AI Product Engineer. Your core responsibilities include designing and maintaining the realtime platform—WebRTC media infrastructure, streaming LLM sessions, and the Python backend. You'll own reliability, performance, and observability of Kulu's core services end-to-end: rooms, agents, audio in/out, recording pipelines, and telemetry that turns user-reported issues into actionable metrics.
You'll manage the LLM streaming session layer as an engineering system, handling connection lifecycle, streaming, reconnection, resumption, tool-call plumbing, timeouts, and watchdogs. You'll own deployment and infrastructure across AWS, drive the infrastructure-as-code programme (OpenTofu), and maintain production systems by triaging incidents, root-causing issues, and feeding learnings back into telemetry and runbooks.
The role includes building and extending the backend (Python/FastAPI/PostgreSQL/Redis/Alembic), shipping product surfaces in React when needed, and handling sensitive meeting data with appropriate privacy and auditability. You'll contribute to architectural decisions as Kulu scales, with focus on system correctness, data integrity, and security. Strong engineering fundamentals—well-tested code, clear data models, graceful degradation—are essential. You ship end-to-end: write migrations, deploy services, and monitor dashboards.
Requirements: 5+ years in Platform Engineering, DevOps, SRE, or backend infrastructure. Strong Python (asyncio, FastAPI) and Bash skills. Hands-on production experience with realtime media infrastructure (LiveKit, Daily, Agora, Pipecat, or WebRTC). Solid AWS operational experience (ECS, IAM, secrets, VPC, networking). CI/CD pipeline experience (GitHub Actions, GitLab CI). Infrastructure-as-code production experience (Terraform/OpenTofu). Distributed systems, event-driven architecture, and fault-tolerant design knowledge. PostgreSQL and Redis production experience. Monitoring/logging tools (Prometheus/Grafana, Datadog, ELK). Infrastructure and application security best practices. Stack comfort including React when needed. Strong AI-tool skills for coding and debugging. Clear systems-level thinking and fluent English.
Nice-to-have: AWS certifications, security compliance experience (SOC 2/ISO 42001), streaming LLM API integration (Gemini Live, OpenAI Realtime), speech pipelines (STT/TTS), eval/model-quality infrastructure support.
