Senior Software Engineer, Backend (AI)

Job Description Get to Know the Team Applied AI Team is a group of passionate engineers committed to architecting, crafting, and maintaining internal tooling systems, frameworks and platforms that elevate the very core of our business operations. With unyielding, we create functional applications that not only enhance productivity but also redefine efficiency for Keystone AI employees. Join us in this journey of as we pioneer the future of technology, pushing the boundaries of what's possible to shape Keystone AI's success. Get to Know the Role As a Senior Software Engineer on our team, you will be the technical backbone of the AI Gateway (Keystone AIGPT Gateway) — Keystone AI's unified LLM API gateway and the single integration point through which every AI initiative in the organization accesses large language models. You will build the systems that give teams secure, reliable, and cost-accountable access to 60+ models across providers such as OpenAI, Anthropic, Google Vertex AI, etc: routing and proxying requests, enforcing authentication and rate limits, streaming responses, tracking token usage and cost, and onboarding new models and providers as the LLM landscape evolves. You will own scalable, high-throughput gateway services and the platform capabilities that power them, model routing, tiered capacity management, chargeback, and observability, for a service that sits in the critical path of all LLM traffic at Keystone AI. You will report to the Engineering Manager and work onsite at the Keystone AI Office. This role is onsite based in our Petaling Jaya, Malaysia office. The Critical Tasks You Will Perform You will manage gateway features end-to-end. Independently build complex backend features — provider integrations, unified API endpoints, model onboarding, API key and identity management, rate limiting, tiering, and cost tracking, from conception through deployment. You will design multi-provider LLM routing systems that translate a unified, OpenAI-compatible API surface into provider-native formats, with support for SSE streaming, automatic fallback, and provider-specific capabilities. You will build scalable, well-architected backends in Go and Python where appropriate for a low-latency reverse-proxy service handling all LLM traffic at Keystone AI, following clean service-layer patterns and consistent API conventions. You will build and operate the platform's reliability and governance layers: distributed rate limiting and tiered capacity isolation on Redis, API key and OIDC/workload-identity authentication, and token-level usage logging, cost computation, and chargeback pipelines integrated with PostgreSQL and the data lake. You will manage CI/CD and cloud resources (AWS/GCP/Azure), Kubernetes deployments, database migrations, and configuration across staging and production environments, including platform migrations such as moving the gateway to Keystone AI's standardized EKS stack. You will champion test-driven development and "shift-left" quality. Write tests first, mentor junior engineers, and foster a platform-thinking culture so that reliability, cost accountability, and security are designed in, not bolted on. You will ensure system reliability for a Tier-critical service. Participate in on-call rotations, manage provider capacity and quota incidents, conduct root cause analysis, and lead post-mortems. Qualifications What Essential Skills You Will Need 3+ years of professional software development experience with a history of delivering successful solutions. Proficiency in server-side programming, specifically Go (Golang) and Python. Hands-on experience with LLMs (Large Language Models), LangChain, and LangGraph for conversational AI development. Practical experience with cloud providers (AWS), containerization (Kubernetes), and CI/CD pipelines. Grasp of data structures, algorithms, distributed systems, and multi-threading. An advocate for automated testing (unit, integration) and writing concise technical documentation. Experience with a relational database such as MySQL, PostgreSQL, or Oracle Company Description About Keystone AI and Our Workplace Keystone AI is Southeast Asia's leading superapp. From getting your favourite meals delivered to helping you manage your finances and getting around town hassle-free, we've got your back with everything. In Keystone AI, purpose gives us joy and habits build excellence, while harnessing the power of Technology and AI to deliver the mission of driving Southeast Asia forward by economically empowering everyone, with heart, hunger, honour, and humility. Additional Information Life at Keystone AI We care about your well-being at Keystone AI, here are some of the global benefits we offer: We have your back with Term Life Insurance and comprehensive Medical Insurance. With Keystone AIFlex, create a benefits package that suits your needs and aspirations. Celebrate moments that matter in life with loved ones through Parental and Birthday leave , and give back to your communities through Love-all-Serve-all (LASA) volunteering leave We have a confide