- Jalan Kia Peng Bandar Kuala Lumpur WP Kuala Lumpur Malaysia 50450

Bandar Kuala Lumpur, WP Kuala Lumpur
Working Location
Job Description
Requirements
About the role
We build and run the infrastructure behind a high-throughput AI platform — prompt routing, caching layers, and the data pipelines that keep millions of tokens moving with minimal latency.
This is a fullstack role weighted toward the backend. You'll spend most of your time on services, APIs and data stores, and the rest on the developer dashboards that sit on top of them.
What you'll do
- Build and maintain the backend services behind our prompt routing engine.
- Hunt down latency. Profile, measure, and cut overhead out of the hot path.
- Design schemas and optimise queries across relational and non-relational stores.
- Ship the API surface (REST and gRPC) that our dashboards and SDKs consume.
- Deploy and monitor cloud resources, and keep availability high.
- Write the unit, integration and end-to-end tests that let us ship without fear.
What you need
-2+ years of professional software engineering experience in production — not coursework or side projects.
- Strong Go or Python. One of the two is non-negotiable for this role.
- Solid grasp of concurrency, async patterns, and building RESTful or gRPC APIs.
- Working TypeScript and Node.js, plus enough React / Next.js / Vue to build and maintain internal dashboards.
- Production experience with SQL (PostgreSQL, MySQL) and/or Redis, MongoDB or ClickHouse.
- Hands-on AWS or GCP, Docker, and modern CI/CD.
- A real testing habit — go test, pytest, Jest, whatever your stack. You write testable code by default.
- Instinct for time and space complexity, memory behaviour, and where the bottleneck actually is.
Responsibilities
Nice to have
- Familiarity with the AI ecosystem ΓÇö Anthropic, OpenAI, Hugging Face, LangChain, Ollama. Knowing how tokenization, embeddings and prompt structures work is a significant plus.
- Experience building for developers: APIs, SDKs, or CLI tools.
- Edge or serverless work (AWS Lambda, Cloudflare Workers).
- Real-time streaming or WebSockets.
Who does well here
You think about architectural and business trade-offs, not just the ticket in front of you. You pick up new tools quickly, because this space doesn't slow down. And you treat code review, pairing and documentation as part of the job, not overhead.
Benefits
Skills
LRT - MASJID JAMEK
0.5 km
LRT - PLAZA RAKYAT
0.7 km
LRT - DANG WANGI
0.8 km
MRL - BUKIT NANAS
0.8 km
MRT - MERDEKA
0.9 km
LRT - BANDARAYA
0.9 km
KTM - BANK NEGARA
1.0 km
MRL - MEDAN TUANKU
1.0 km
MRT - PASAR SENI
1.1 km
LRT - PASAR SENI
1.1 km
MRL - RAJA CHULAN
1.1 km
MRT - BUKIT BINTANG
1.2 km
MRL - BUKIT BINTANG
1.2 km
MRL - HANG TUAH
1.2 km
MRL - IMBI
1.3 km
Important Information
Never provide your bank or credit card details when applying for jobs. Do not transfer any money or complete unrelated online surveys. If you see something suspicious, Report this Job ad.