AI Application Full Stack Engineer

Mekari · Jakarta Pusat, Dki Jakarta, Indonesia

Lamar

Sekilas tentang pekerjaan ini

Mekari mencari AI Application Full Stack Engineer untuk membangun dan mengoperasikan platform inferensi, integrasi model, serta sistem evaluasi AI. Posisi di Jakarta Pusat ini membutuhkan pengalaman minimal 4 tahun dalam rekayasa perangkat lunak web produksi.

Tugas utama

  • Merancang API REST/streaming dan arsitektur platform berkeamanan tinggi.
  • Mengintegrasikan model AI dan membangun agent serta model khusus.
  • Mengoptimalkan routing, throughput, latensi, dan biaya inferensi.
  • Menyusun evaluasi, tolok ukur, dan rilis model yang aman.
  • Menjaga observabilitas, privasi data tenant, dan dokumentasi teknis.

Kualifikasi utama

  • Pengalaman minimal 4 tahun dalam rekayasa perangkat lunak web produksi.
  • Menguasai TypeScript/JavaScript, Node.js, PostgreSQL, dan desain API REST.
  • Berpengalaman membangun fitur LLM produksi, RAG, dan alur kerja agent.
  • Berpengalaman dengan Docker, Kubernetes, CI/CD, cloud, dan keamanan API.
  • Mampu bekerja mandiri dan berkolaborasi dengan tim AI dan produk.

Ringkasan ini dibuat dengan AI dari deskripsi di bawah. Yang berlaku adalah deskripsi lengkapnya di situs Mekari.

Deskripsi pekerjaan

Mekari is Indonesia's no. 1 Software-as-a-Service (SaaS) company. With our ecosystem of software solutions—including Mekari Jurnal, Mekari Talenta, Mekari Qontak, and Mekari Flex, we aim to facilitate entrepreneurs and leaders as they accelerate the digital transformation of their businesses.

In our 10+ years of journey we have reached over 3 Million platform users, and we're not planning to stop any time soon. We need more people like you: builders and owners with calculated ambition who are ready to #ElevateThroughImpact and raise Indonesia's software standard.

How the Role Ships End-to-End

  • Platform Shipping: Build and run secure, observable inference APIs, routing policies, tenant controls, metering, and operator control surfaces.
  • Intelligence Supply: Deliver versioned agent drivers, task-specific small models, prompts, tools, and retrieval pipelines for product integration.
  • Evaluation & Feedback: Use production data, benchmarks, quality gates, and cost metrics to continuously improve models, routing, and guardrails.

Core Responsibilities

  • API & Platform Architecture: Design high-concurrency REST/streaming APIs, handle auth (OAuth2), RBAC, tenant isolation, fallbacks, metering, and PostgreSQL data modeling.
  • Model & Agent Delivery: Integrate provider/self-hosted models, maintain versioned capability catalogues, and build lightweight, task-specific models and agent drivers.
  • Routing & Optimization: Run policy-aware routing, run benchmarks across prompt/output variations, and optimize throughput, latency, and token economics.
  • Evaluation & Safety: Partner with experts to curate task datasets, set release thresholds, run baseline comparisons, and deploy shadow/staged releases safely.
  • Operations & Governance: Maintain observability dashboards, alerts, runbooks, cost controls, tenant data privacy, clear technical documentation, and code quality.

Typical Deliverables

  • Production inference APIs, web control surfaces, tenant quota controls, and accurate usage metering.
  • Versioned model integrations, fallback execution rules, capacity plans, and performance benchmarks.
  • Task-specific model endpoints and agent drivers with clear contracts, owners, and versioning.
  • Evaluation datasets, release gates, regression checks, and observability runbooks.
  • Technical design notes detailing model selection, routing logic, trade-offs, and unit economics.

Success Measures

  • Adoption & Usability: Growing adoption across product teams through a single governed, reusable platform path.
  • Quality & Safety: Higher task success rates alongside strict adherence to safety, quality, and tenant policy boundaries.
  • Economic & Performance Efficiency: Lower cost and latency per completed task, driven by smaller models and optimized routing.
  • Reliability & Agility: Reversible, progressive releases with early detection of regressions, anomalies, or capacity bottlenecks.

Requirements

Engineering & Architecture

  • Core Stack: 4+ years in production web software engineering. Strong TypeScript/JavaScript and Node.js; production frontend experience (Vue preferred, or React/Next.js); working knowledge of Go.
  • Databases & APIs: Production PostgreSQL expertise (schema design, indexing, query optimization, transactions); strong REST API design with streaming and long-lived connections.
  • Best Practices: High testing standards (TDD mindset), constructive code review, and practical knowledge of microservices design patterns and their trade-offs.

Production & Infrastructure

  • Scalability & Security: Proven ownership of high-traffic scalability, API gateways, load balancing, and SLA/SLO tracking. Strong security practices (OAuth2, RBAC, tenant isolation, least privilege).
  • DevOps & Cloud: Hands-on with Docker, Kubernetes, Helm, CI/CD pipelines, Git workflows, and major public clouds (Alibaba Cloud, AWS, GCP, or Azure).

AI, Inference & Agents

  • Production LLM Experience: Track record of shipping real-world LLM features, multi-provider API integrations (OpenAI, Anthropic, aggregators), function calling, RAG/vector DBs, multimodal inputs, and batch/file APIs.
  • Inference & Self-Hosting: Experience operating self-hosted models using inference engines (vLLM, TGI, Triton). Ability to profile queuing, TTFT, generation speed, context limits, and unit costs.
  • Agents, Tuning & Eval: Experience building multi-step agent workflows with guardrails, prompt engineering, and small task-specific model tuning. Rigorous evaluation habits (benchmarking, regression suites, error analysis).
  • Cost & Tooling: Focus on latency/cost per completed task (not just token cost). Proficiency with AI coding assistants (e.g., Claude Code, Codex) paired with strict code review discipline.

Collaboration & Process

  • Strong written/verbal communication, independent execution from problem framing to deployment, and collaborative teamwork with AI/product teams using Scrum or Kanban.

Nice to Have

  • Multi-GPU/multi-node model deployment or fine-tuning.
  • Microfrontend architectures (Module Federation, single-spa).
  • Ruby frameworks (Rails, Sinatra).
  • Experience building internal developer platforms (IDPs) or developer-facing APIs.

Our team will review your application and will be in touch if your application is shortlisted to the next stage. If you do not hear from us in 30 days, we will keep your resume on file in case a relevant opportunity opens up.

Don't forget to check our Recruitment FAQ at bit.ly/FAQMekariHiringENG or bit.ly/FAQMekariHiringINA to find the answers to commonly asked questions regarding our recruitment process.

We wish you the best. Hope to see you around soon!

Lowongan ini diambil dari situs karier resmi Mekari. Lokr tidak memproses lamaran: kamu melamar langsung di situs perusahaan, dan info terbaru tentang lowongan ini ada di sana.

Lowongan lain di Mekari

Lowongan Komputer & Perangkat Lunak di perusahaan lain