AI Application Full Stack Engineer
Mekari (PT. Mid Solusi Nusantara)2 days ago
Remote, Indonesia or Jakarta, IndonesiaMid Level
Responsibilities
- Design and build secure REST APIs, real-time streaming endpoints, backend services, and operator-facing web interfaces.
- Build and operate a unified API gateway for external and self-hosted models with routing, load balancing, and failover.
- Implement authentication, role-based access control, quotas, rate limits, tenant isolation, and accurate usage and cost measurement.
- Design PostgreSQL schemas and queries for correctness, performance, and billing needs.
- Operate reliable, scalable production systems with instrumentation, availability targets, progressive rollouts, and incident debugging.
- Develop and deploy LLM-backed features, agent workflows, model integrations, and self-hosted model infrastructure.
- Participate in code review, testing, CI/CD, release and rollback processes, documentation, and post-mortems.
- Collaborate with product managers, technical program management, DevOps, product teams, and AI engineers.
- Mentor engineers and improve design and code quality.
Requirements
- At least 4 years of software engineering experience building and running production web applications.
- Strong JavaScript and TypeScript skills with production Node.js experience.
- Production experience with a modern frontend framework; Vue is preferred, while React or Next.js is also accepted.
- Working knowledge of Go and production PostgreSQL experience covering schema design, indexing, transactions, and query diagnosis.
- Experience designing REST APIs, streaming responses, long-lived connections, testing, code review, and microservices.
- Experience with scalability, reliability, API gateways, load balancing, availability targets, and error-rate targets.
- Knowledge of OAuth2, role-based access control, credential handling, tenant isolation, input validation, and least privilege.
- Experience with Docker, Kubernetes, Helm, Git-based workflows, release and rollback processes, and at least one of Alibaba Cloud, AWS, GCP, or Azure.
- Experience shipping LLM-backed features to real users and working with model providers such as OpenAI and Anthropic.
- Understanding of streaming responses, tool and function calling, embeddings, RAG, vector databases, multimodal input, and provider batch and file APIs.
- Experience operating self-hosted models with inference servers such as vLLM, SGLang, TGI, or Triton.
- Experience building agent workflows, evaluating model output, and managing cost and latency constraints.
- Working proficiency with AI-assisted development tools such as Claude Code or Codex.
- Experience collaborating with product teams and AI engineers, independently taking solutions from problem framing to production, and communicating clearly.
- Familiarity with Scrum and Kanban.
- Preferred qualifications include multi-GPU or multi-node model deployment, model fine-tuning, microfrontend architectures, Ruby frameworks such as Rails or Sinatra, and internal developer platforms or APIs.
Tech Stack
Alibaba CloudAWSAzureDockerGoGoogle Cloud PlatformHelmJavaScriptKubernetesNext.jsNode.jsPostgreSQLReactRubyRuby on RailsTypeScriptVue.js
Categories