Candidate Match
See which software roles match your experience and where the strongest opportunities are.
Python, FastAPI, PostgreSQL, Docker, Redis, Celery & scalable REST APIs.
PyTorch, Hugging Face, pgvector, LangChain, RAG pipelines & embeddings.
React, TypeScript, Node.js, Next.js, PostgreSQL, Tailwind & modern state.
Kubernetes, AWS, Terraform, Docker, Go, Linux systems & CI/CD infrastructure.
No analysis yet
Paste your profile or choose a sample profile above to see your strongest matches, score decomposition, and skill gaps.
Jobs
-- rolesSearch software roles by skills, technologies and experience. (Powered by hybrid search)
Market
Explore skill demand, seniority and location trends across the current dataset.
How SkillPulse works
A transparent 5-step pipeline from multi-market job collection to explainable candidate matching.
Ingestion
Jobs are ingested from multiple sources across European (Arbeitnow, Remotive, Himalayas, Jobicy) and Latin American markets.
Extraction
Structured requirements are extracted through deterministic keyword tries and model-assisted extraction pipelines.
Taxonomy
Skills are mapped to canonical ESCO / O*NET concepts (e.g. reactjs → React, postgres → PostgreSQL).
Retrieval
Lexical and semantic retrieval are combined using Reciprocal Rank Fusion ($k=60$) on PostgreSQL pgvector.
Matching
Candidate-job fit is calculated using explainable signals: 50% Hard Skills + 20% Role Alignment + 30% Dense Similarity.
Technical architecture & specifications [ View architecture ↓ ]
POSTGRESQL 16 + PGVECTOR
├── Lexical Indexing: English & Portuguese Full-Text Search (tsvector)
├── Dense Vector Search: 384-dimensional Embeddings (HNSW Index, Cosine Distance)
└── Reciprocal Rank Fusion: RRF(d) = 1 / (60 + rank_lexical) + 1 / (60 + rank_vector)
AI & EXTRACTION STACK
├── Tier 1: Deterministic Aho-Corasick Keyword Trie
├── Tier 2: Contextual Token Extraction (JobBERT / Token Classifier)
├── Tier 3: Cloud AI Router (Groq & OpenRouter) with structured JSON schemas
└── Normalization: Canonical ESCO / O*NET Skill Taxonomies
SkillPulse uses FastAPI, PostgreSQL/pgvector, hybrid retrieval, and model-assisted extraction.