AI-powered career decision support for job seekers in Indonesia.
Bisakerja is a web-based Career Decision Engine designed to help Indonesian job seekers make better, faster, and more informed career decisions.
The project focuses on a common problem in the job search process: vacancies are spread across multiple platforms, users often apply through trial and error, and there is little visibility into whether a role truly matches their skills, experience, and preferences. As a result, job seekers waste time on low-fit opportunities, miss better options, and lack clear guidance on what to improve next.
Bisakerja addresses this gap by combining job aggregation, profile-based matching, skill gap analysis, and application tracking into one decision support experience. Instead of functioning as a simple job listing platform, Bisakerja is built to help users understand:
- which roles are worth pursuing
- why a role fits or does not fit
- which skills should be improved first
- how their application strategy should evolve over time
Bisakerja is designed around a practical user journey for job seekers:
- Onboarding with profile, CV, and career preferences
- Job discovery with search, filters, and structured vacancy details
- Explainable job fit scoring for each relevant opportunity
- Skill gap analysis with clear improvement priorities
- Career strategy recommendations and readiness insights
- Application tracking with feedback loops for better decisions
The platform also includes supporting flows such as bookmarking, notifications, profile management, mentoring discovery, and AI CV analysis as part of the broader product direction.
| Feature | Description |
|---|---|
| Job Aggregation | Collects and structures job vacancies from selected sources so users can discover opportunities more efficiently. |
| Search and Filtering | Supports job search by title, location, work type, expertise, salary range, and other relevant filters. |
| User Preferences | Stores target role, preferred location, work type, skills, salary expectation, and job-seeking timeline. |
| Job Fit Scoring | Generates a score from 0 to 100 based on skill match, experience match, and preference match. |
| Explainable Match Breakdown | Shows the reasoning behind the score so users can understand strengths and gaps instead of receiving a black-box result. |
| Skill Gap Analysis | Identifies missing skills, ranks them by priority, and provides basic learning direction. |
| Career Strategy Recommendation | Recommends whether a role is worth applying for now, what to improve first, and how ready the user is. |
| Application Tracker | Tracks statuses such as applied, interview, rejected, and accepted to build a continuous feedback loop. |
| AI CV Analyzer | Compares a CV against a selected job listing, reviews ATS readiness, keyword fit, and improvement actions. |
| Mentoring Discovery | Enables users to discover mentors, review expertise, and access mentoring-related information. |
- Fresh graduates in digital and technology-related fields
- Early-career professionals with 0 to 3 years of experience
- Career switchers moving into digital or technology roles
The current MVP direction centers on:
- Basic job aggregation
- Job search and structured vacancy detail pages
- Authentication and onboarding
- User preference management
- Job fit scoring
- Skill gap analysis
- Basic career strategy recommendations
- Application tracking
- Native mobile applications
- Automatic application submission to external platforms
- Direct ATS integration with employers
- Advanced OCR-heavy CV processing
- Payment infrastructure
The broader product journey includes:
- Authentication and account creation, including email verification and optional Google sign-in.
- Job seeker onboarding covering profile setup, CV upload, and career preferences.
- Job exploration through search, filters, saved jobs, and detailed vacancy pages.
- AI-assisted decision support through fit scoring, skill gap analysis, and CV analysis.
- Application tracking and notifications for continuous progress monitoring.
- Profile and career preference updates as the user's goals evolve.
| Component | Technology |
|---|---|
| Frontend | React, Next.js, Tailwind CSS |
| Backend API | Express.js, TypeScript |
| AI Services | Python, FastAPI, TensorFlow, Sentence-Transformers, rule-based scoring |
| Database | PostgreSQL |
| ORM | Prisma |
| Authentication | Email-based authentication, OTP verification, optional Google sign-in |
| Infrastructure | Docker, GitHub, deployment to web infrastructure |
Bisakerja is being developed as a capstone project under Coding Camp 2026 powered by DBS Foundation with the theme Future-Ready Work and Economy.
The delivery plan is structured around these milestones:
| Milestone | Focus |
|---|---|
| M1 | Foundation setup, dataset preparation, and UI/UX direction |
| M2 | Data scraping and frontend slicing |
| M3 | Automation and model training |
| M4 | Validation, explainable AI, and tracker development |
| M5 | AI and backend integration |
| M6 | Testing and finalization |
Bisakerja is in active development as a web-based MVP.
Current priorities include:
- Building a reliable job data pipeline
- Delivering transparent job fit scoring
- Validating skill gap analysis outputs
- Integrating AI services into the end-to-end product flow
- Refining the user experience for search, analysis, and tracking
Bisakerja is developed by team CC26-PSU263:
- Tasya Anggraeni Firdaus — Data Scientist
- Dzikri Albantani — Data Scientist
- Salman Abdurrahman — Full-Stack Web Developer
- Agel Saputra — Full-Stack Web Developer
- Linda David — AI Engineer
Bisakerja is built on a simple belief: job seekers need more than vacancy listings. They need clear signals, explainable insights, and practical recommendations that help them decide what to apply for, what to improve, and what to do next.
