About the role
Architect and scale high-throughput, low-latency API gateways powering enterprise AI model inference
Own end-to-end backend development across Go/Python microservices, GPU orchestration, and open-source inference engines
About the company
As an innovative leader in artificial intelligence infrastructure, this organization builds developer-first platforms that simplify access to foundation models. The company is committed to advancing scalable cloud-native technologies, empowering global enterprises to deploy reliable AI applications seamlessly.
About the job
Your role involves:
Architecting and evolving a fault-tolerant, secure backend platform that serves enterprise AI inference workloads at scale
Building core platform services including unified API protocol layers, identity and access management, dynamic request routing, and usage metering/billing engines
Designing seamless technical integrations to connect the inference platform with diverse enterprise client environments
Implementing deep system observability while continuously optimizing service latency, compute efficiency, and overall platform reliability
Evaluating and integrating emerging open-source AI inference technologies into production workflows to elevate system throughput
Driving full-lifecycle software delivery—from architectural design and automated testing to production rollout and root cause incident analysis
Skills and experience required
As a successful applicant, you will have:
Master's or PhD in Computer Science/Engineering (or equivalent experience) with 5+ years of backend engineering experience in large-scale or AI infrastructure
Strong programming expertise in Go, Python, or comparable systems-level backend languages
Deep hands-on mastery of distributed systems, microservices architecture, middleware, and network protocols in high-availability production environments
Practical working knowledge of GPU computing concepts, AI inference architectures, Linux, containers, and Kubernetes orchestration
Proven engineering judgment to balance system reliability, performance optimization, architectural complexity, and delivery velocity
Production experience integrating inference frameworks (such as vLLM, TensorRT-LLM, or SGLang) or optimizing distributed GPU model serving (Advantage)
Whats on offer
Shape the foundational architecture of an AI-native platform used by developers and enterprises to run next-generation models in production. You will thrive in a high-ownership engineering culture that encourages continuous experimentation with cutting-edge open-source inference stacks.
To apply online please use the 'apply' function, alternatively you can reach me at https://www.linkedin.com/in/hoonteck-nologyrecruitment. (EA: 94C3609/ R1219669)