Senior AI/Data Engineer Needed to Build MVP (Entity Resolution + Risk Scoring) – 4 Week Project
Budget: $750 – $1,500 USD
Senior AI/Data Engineer Needed to Build MVP (Entity Resolution + Risk Scoring) – 4 Week Project
Overview:
I am building a financial intelligence platform focused on entity resolution and risk detection across large datasets (similar to Palantir-style systems).
I am looking for one highly skilled engineer to build a functional MVP in 4 weeks.
This is not a basic project. You must be able to operate independently and deliver production-quality work fast.
⸻
Scope of Work (MVP Only):
You will build a working system that can:
1. Data Ingestion
• Ingest structured datasets (CSV/API)
• Normalize and store data
2. Entity Resolution (CORE FEATURE)
• Match entities across datasets (names, companies, aliases)
• Implement fuzzy matching or embedding-based similarity
• Return confidence scores for matches
3. Basic Risk Scoring
• Assign a simple risk score based on:
• Matches to flagged entities
• Relationship proximity (basic graph logic)
• Output must be explainable
4. Search Interface
• Simple UI or API where user can:
• Search a name/entity
• See matched entities
• View risk score + reasoning
⸻
Deliverables (End of 4 Weeks):
• Fully working MVP (hosted or runnable locally)
• Clean, documented codebase
• API endpoints for search + scoring
• Basic UI (can be minimal but functional)
⸻
NON-NEGOTIABLE SKILLS
You must have real experience in:
Core Engineering
• Python (advanced)
• API development (FastAPI or Flask)
• Working with large datasets
AI / Data
• Entity resolution / fuzzy matching
• Embeddings (e.g. OpenAI, sentence transformers)
• Basic machine learning or scoring systems
Data Infrastructure
• PostgreSQL or similar database
• Building ETL/data pipelines
Systems / Architecture
• Ability to design a simple but scalable architecture
• Experience deploying applications (AWS, GCP, or similar)
⸻
BONUS (STRONGLY PREFERRED)
• Experience with graph databases (Neo4j)
• Experience with financial, AML, or KYC datasets
• Experience building search systems
⸻
Timeline:
• Total: 4 weeks
• Week 1: Data ingestion + schema
• Week 2: Entity resolution working
• Week 3: Risk scoring + API
• Week 4: UI + deployment + polish
⸻
Compensation:
• Fixed project fee (based on experience)
• Bonus for early or high-quality delivery
⸻
How to Apply (IMPORTANT):
To be considered, you must include:
1. Examples of similar work (data systems, AI, search, etc.)
2. Your exact approach to building this MVP
3. Tech stack you would use
4. Confirmation you can deliver in 4 weeks
Applications without this will be ignored.
Overview:
I am building a financial intelligence platform focused on entity resolution and risk detection across large datasets (similar to Palantir-style systems).
I am looking for one highly skilled engineer to build a functional MVP in 4 weeks.
This is not a basic project. You must be able to operate independently and deliver production-quality work fast.
⸻
Scope of Work (MVP Only):
You will build a working system that can:
1. Data Ingestion
• Ingest structured datasets (CSV/API)
• Normalize and store data
2. Entity Resolution (CORE FEATURE)
• Match entities across datasets (names, companies, aliases)
• Implement fuzzy matching or embedding-based similarity
• Return confidence scores for matches
3. Basic Risk Scoring
• Assign a simple risk score based on:
• Matches to flagged entities
• Relationship proximity (basic graph logic)
• Output must be explainable
4. Search Interface
• Simple UI or API where user can:
• Search a name/entity
• See matched entities
• View risk score + reasoning
⸻
Deliverables (End of 4 Weeks):
• Fully working MVP (hosted or runnable locally)
• Clean, documented codebase
• API endpoints for search + scoring
• Basic UI (can be minimal but functional)
⸻
NON-NEGOTIABLE SKILLS
You must have real experience in:
Core Engineering
• Python (advanced)
• API development (FastAPI or Flask)
• Working with large datasets
AI / Data
• Entity resolution / fuzzy matching
• Embeddings (e.g. OpenAI, sentence transformers)
• Basic machine learning or scoring systems
Data Infrastructure
• PostgreSQL or similar database
• Building ETL/data pipelines
Systems / Architecture
• Ability to design a simple but scalable architecture
• Experience deploying applications (AWS, GCP, or similar)
⸻
BONUS (STRONGLY PREFERRED)
• Experience with graph databases (Neo4j)
• Experience with financial, AML, or KYC datasets
• Experience building search systems
⸻
Timeline:
• Total: 4 weeks
• Week 1: Data ingestion + schema
• Week 2: Entity resolution working
• Week 3: Risk scoring + API
• Week 4: UI + deployment + polish
⸻
Compensation:
• Fixed project fee (based on experience)
• Bonus for early or high-quality delivery
⸻
How to Apply (IMPORTANT):
To be considered, you must include:
1. Examples of similar work (data systems, AI, search, etc.)
2. Your exact approach to building this MVP
3. Tech stack you would use
4. Confirmation you can deliver in 4 weeks
Applications without this will be ignored.
Related categories:
Python
PostgreSQL
Flask
Documentation
ETL
Neo4j
API Development
FastAPI
OpenAI
AI Development