Freelancers using Next.js in JakartaFreelancers using Next.js in Jakarta
ProjectsPeople
Kelvin Desman's avatar
Kelvin Desman
Jakarta, Indonesia
Mind of an engineer and the heart of an entrepreneur.
$50k+
Earned
1x
Hired
11
Followers
Mind of an engineer and the heart of an entrepreneur.
Cover image for For every feature I shipped
For every feature I shipped with an AI agent, I shipped more than two fixes. 1,000+ PRs. 84 days. Solo. The throughput was real — but 360 of those PRs were fixes against 150 features. That ratio is the part nobody puts in their recap post. The core problem: the agent is a 20× author, not a 20× reviewer. I had no leverage on verification — just guards built from past failures, useless against anything new. What I'd change: second agent for adversarial review only, and changes small enough that being wrong is cheap. Agentic engineering doesn't remove the hard part. It moves it.
1
63
Cover image for Optimize Remote Job Applications for Indonesian Developers w...
Built a RAG job-hunting agent for Indonesian developers applying to remote USD jobs. 28 days of real usage. Here's what I learned. The problem: applying to 50+ remote jobs manually is exhausting. Wrong roles, no resume tailoring, hours wasted per application. The workflow now: One message → agent retrieves relevant jobs → ranks them → generates tailored resume + cover letter → user approves or skips. Stack (still running $0 free tier): · Embeddings: Cloudflare Workers AI qwen3-embedding-0.6b · Vector search: Cloudflare Vectorize, cosine similarity · Database: Cloudflare D1 / SQLite, one batched query · Semantic cache: Cloudflare KV, cosine ≥0.92 threshold · LLM: JSON-mode slot extraction + reply Only variable cost: ~$0.002/turn LLM usage 28-day numbers: · 235 sessions · 329 return visits · 743 agent turns · 357 job cards surfaced → 46 approved applications ~20 approvals per 100 sessions (target was 10–15) Total LLM cost: ~$1–4 Example matches from one natural-language query: Linear — 96/100 · DatAds — 95/100 · Spotify — 100/100 Two decisions I'd make again: · The scorer is deterministic — pure function, 7 weighted components, 0–100. No model drift. Users see exactly why a job scored highly. I didn't trust LLM ranking for something this consequential. · There's a regex fallback behind every LLM extraction. If the model fails or times out, the conversation continues. Users never hit a dead end. What's next: · Tracking downstream outcomes — recruiter replies, interviews Detecting expired/duplicate posts more aggressively Calibrating scoring weights from real approval behavior · The pipeline runs cheaply and generates real approvals. The next challenge is proving it improves actual job outcomes — not just application volume. This is the kind of system I enjoy building: AI-native product on constrained infra, with real users and measurable north-star metrics. If you're working on something similar — hiring pipelines, talent matching, AI agents for job seekers — I'd enjoy comparing notes. And if you're an Indonesian dev hunting remote USD roles, the product is live at lokerdollar.com (http://lokerdollar.com). What would you build differently? 👇 #RAG (https://www.linkedin.com/search/results/all/?keywords=%23rag&origin=HASH_TAG_FROM_FEED) #CloudflareWorkers (https://www.linkedin.com/search/results/all/?keywords=%23cloudflareworkers&origin=HASH_TAG_FROM_FEED) #BuildInPublic (https://www.linkedin.com/search/results/all/?keywords=%23buildinpublic&origin=HASH_TAG_FROM_FEED) #AIEngineering (https://www.linkedin.com/search/results/all/?keywords=%23aiengineering&origin=HASH_TAG_FROM_FEED) #RemoteJobs (https://www.linkedin.com/search/results/all/?keywords=%23remotejobs&origin=HASH_TAG_FROM_FEED) #IndonesianDevelopers (https://www.linkedin.com/search/results/all/?keywords=%23indonesiandevelopers&origin=HASH_TAG_FROM_FEED)
3
114
Cover image for Most LLM telemetry posts brag
Most LLM telemetry posts brag about what they monitor. Here's mine — including what I'm still missing. Built this for lokerdollar.com (http://lokerdollar.com), solo, in production: Covered: — p50 / p95 / p99 latency per task — cost per 1k tokens + daily burn + per-task spend — provider success rates + circuit breaker state — cache hit rate, quota / rate limit tracking — model leaderboard scored on live traffic Gaps I'm still chasing: — prompt versioning tied to quality signals — TTFT for streaming UX (matters for chat tasks) — per-user cost attribution — semantic error taxonomy, not just HTTP codes — push-based degradation alerts (today's playbook is reactive) The lesson from running this solo: observability is never "done." It's a backlog that evolves with the product — and the gap list is more honest signal than the green checkmarks. → Open for AI platform / full-stack work. If you want this layer for your team, my DMs are open.
1
64
Cover image for LokerDollar.com
LokerDollar.com
0
7
Next.js(8)
Nemesis 's avatar
Nemesis
Jakarta, Indonesia
I’m a web developer who can build clean, functional, and mod
I’m a web developer who can build clean, functional, and mod
Cover image for Course App
Course App
0
78
Cover image for Company Management Dashboard - Factory 2.0
Company Management Dashboard - Factory 2.0
1
130
Cover image for Business Management Platform Development
Business Management Platform Development
0
5
Cover image for Greenfood App
Greenfood App
0
2
Next.js(5)
Componine Creative's avatar
Componine Creative
proJakarta, Indonesia
Brand, Website, Product, Motion, & Development for Startups
$25k+
Earned
10x
Hired
5.0
Rating
6
Followers
Brand, Website, Product, Motion, & Development for Startups
Cover image for For years we helped other
For years we helped other startups and studios to build other people's websites, products & brands. Today we're launching Componine Creative Studio. A few things we care about: → Staying close to the work. You'll talk to the founder directly, not someone passing your brief down a chain. → Keeping things under one roof. Web, product, brand, motion, all in the same place. → Quality over quantity. We only take on a limited number of projects at a time, so nothing gets rushed or watered down. New site is live. Visit Componine.com (https://www.componine.com/)
0
222
Cover image for Design a Brand & Website for Componine Creative Studio
Design a Brand & Website for Componine Creative Studio
0
12
Cover image for Design a Brand, Website & Product for Baxso Management Tool
Design a Brand, Website & Product for Baxso Management Tool
0
4
Cover image for Web3/AI Rebrand and Product Design for Hub
Web3/AI Rebrand and Product Design for Hub
0
5
Next.js(1)
Septian A. Tama's avatar
Septian A. Tama
Jakarta, Indonesia
7+ years building optimized web products
$5k+
Earned
2x
Hired
2
Followers
7+ years building optimized web products
Cover image for Quipper Campus
Quipper Campus
0
32
Cover image for COHIVE's Member Dashboard
COHIVE's Member Dashboard
0
4
Cover image for COHIVE's Company Website
COHIVE's Company Website
0
29
Cover image for COHIVE's Blog
COHIVE's Blog
0
4
Next.js(3)
Naufal Rabbani's avatar
Naufal Rabbani
proBekasi, Indonesia
Full Stack Web Developer | UI Designer
Full Stack Web Developer | UI Designer
Cover image for Annur School
Annur School
1
5
Cover image for Legenda Permata
Legenda Permata
1
6
Cover image for Neuromage
Neuromage
1
2
Placeholder project card media
View more →
Next.js(3)
Fadhil Akbar's avatar
Fadhil Akbar
Jakarta, Indonesia
Frontend Dev | React/Next.js | Fast & Modern UI
Frontend Dev | React/Next.js | Fast & Modern UI
Cover image for DevOverflow – StackOverflow Clone with Gemini Integration
DevOverflow – StackOverflow Clone with Gemini Integration
0
6
Cover image for AI SEO – Animated Landing Page with Framer Motion & Tailwind
AI SEO – Animated Landing Page with Framer Motion & Tailwind
0
14
Cover image for Sushiman Japanese Food Landing Page Development
Sushiman Japanese Food Landing Page Development
0
5
Placeholder project card media
View more →
Next.js(2)