Fractional Technical Lead / Architect for Crypto AML/KYT Wallet Intelligence Platform

We are looking for a Fractional Technical Lead / Software Architect with strong hands-on experience in crypto AML/KYT, blockchain analytics, wallet screening, transaction monitoring, blockchain intelligence, on-chain risk scoring, or crypto compliance infrastructure. We are building a platform in the category of crypto wallet intelligence and AML/KYT risk analysis. The product is intended to help users, businesses, and financial/crypto services evaluate blockchain addresses, detect risky counterparties, understand money flow, identify exposure to suspicious entities, and receive explainable risk assessments before interacting with a wallet or transaction. The platform is conceptually similar to products in the broader category of: - crypto AML/KYT tools; - wallet screening platforms; - blockchain intelligence platforms; - transaction monitoring systems; - blockchain forensic investigation tools; - on-chain risk scoring systems; - crypto compliance infrastructure; - wallet reputation and risk assessment platforms. We are not looking for a pure compliance analyst, AML investigator, or smart contract developer. We are looking for a technical specialist who understands how such systems should be architected and built. The ideal candidate has previously worked on, designed, or significantly contributed to a system involving: - crypto wallet screening; - transaction monitoring; - blockchain analytics; - blockchain intelligence; - wallet/entity risk scoring; - AML/KYT infrastructure; - address clustering; - entity attribution; - on-chain graph analysis; - OSINT enrichment; - sanctions/scam/phishing/ransomware/mixer exposure detection; - explainable risk assessment. This is a senior-level role. We need someone who can review the current technical direction, identify architectural gaps, validate the risk model, improve the data and evidence model, and help define a practical roadmap toward a production-ready MVP. --- Important Clarification This is not a Solidity-only, NFT, token launch, trading bot, meme coin, or generic Web3 project. We are not looking for someone whose primary experience is only: - writing smart contracts; - launching tokens; - building NFT marketplaces; - developing trading bots; - doing DeFi arbitrage; - managing Telegram crypto communities; - performing manual AML investigations without software engineering experience. Those backgrounds may be helpful as secondary experience, but they are not enough for this role. We need a hands-on technical architect / senior backend-data engineer with experience or strong understanding of how crypto AML/KYT and blockchain intelligence platforms are actually built. --- Project Context We are developing a crypto wallet intelligence and risk analysis platform that evaluates blockchain addresses and transactions using a combination of: - on-chain transaction data; - address/entity labels; - public and commercial intelligence sources; - OSINT enrichment; - risk indicators; - transaction graph analysis; - direct and indirect exposure logic; - risk scoring; - explainable risk factors; - customer-facing recommendations. The system is intended to answer questions such as: - Is this wallet associated with scams, phishing, ransomware, darknet activity, sanctions, mixers, hacks, exploits, or other suspicious behavior? - Has this wallet interacted directly or indirectly with high-risk entities? - What is the level of confidence behind each risk signal? - Which source produced the evidence? - Is the risk direct, inherited, contextual, or only a candidate signal? - Should a user proceed, review manually, or avoid interacting with this wallet? - How should risk be explained in a way that is technically correct, auditable, and useful for customers? The platform is expected to combine multiple layers: 1. Data ingestion and enrichment 2. Wallet/entity evidence collection 3. Source confidence and evidence admission 4. Address and entity labeling 5. On-chain exposure analysis 6. Risk scoring 7. Customer-facing explanations 8. Operational monitoring and data quality metrics 9. Production readiness and scalability We already have an engineering direction and early technical implementation. We need a senior technical expert to audit, improve, and guide the system toward a robust MVP and production launch. --- Role Overview We are seeking a fractional technical lead / architect who can work with us on a part-time or project-based basis. The role may include: - reviewing the existing architecture; - assessing whether the current system design is suitable for a crypto AML/KYT platform; - identifying missing components; - validating the risk-scoring approach; - reviewing the evidence model and source-confidence model; - advising on data ingestion and enrichment strategy; - improving the approach to wallet labels and entity attribution; - defining direct vs indirect exposure logic; - helping design explainable risk outputs; - reviewing the backend and data pipeline architecture; - estimating production-readiness; - defining a practical roadmap for MVP launch; - decomposing the work into engineering tasks; - recommending what specialists are needed next; - optionally contributing hands-on to backend, data, or risk-engine implementation. We do not expect the candidate to do everything alone. However, we expect the candidate to be able to act as a technical authority for this product category. --- Key Responsibilities 1. Architecture Review Review the current architecture of the platform and assess whether it is suitable for a crypto AML/KYT wallet intelligence product. This may include reviewing: - backend services; - data ingestion pipelines; - wallet analysis flow; - risk scoring flow; - API structure; - database schema; - data models; - evidence models; - enrichment logic; - source integration approach; - transaction graph logic; - scalability assumptions; - deployment and infrastructure assumptions. Expected output: - identify architectural strengths and weaknesses; - highlight critical production risks; - identify missing components; - propose improved architecture where needed; - recommend what should be simplified, removed, postponed, or prioritized. --- 2. Risk Scoring and KYT Logic Review Review or help design the wallet risk-scoring methodology. The platform needs to evaluate risk signals such as: - sanctions exposure; - scam exposure; - phishing exposure; - ransomware exposure; - darknet marketplace exposure; - mixer/tumbler exposure; - bridge and chain-hopping behavior; - hacked/exploited funds; - high-risk counterparties; - suspicious transaction patterns; - exposure to known malicious services; - indirect exposure through transaction paths; - low-confidence or unverified allegations; - benign but high-volume services such as exchanges, bridges, payment processors, and DeFi protocols. The candidate should help define how these signals should affect risk score, severity, confidence, and customer-facing explanations. We are especially interested in practical experience with: - direct vs indirect exposure; - hop distance; - graph-based risk propagation; - risk contamination prevention; - known-service protection; - evidence confidence; - false-positive reduction; - explainable risk cards; - deterministic vs probabilistic signals; - manual review thresholds; - customer-visible vs internal-only risk. Expected output: - risk-scoring review; - improved scoring principles; - severity/confidence recommendations; - false-positive prevention recommendations; - guidance on what should and should not be customer-facing. --- 3. Evidence and Source Confidence Model A major part of this product is deciding which external signals can be trusted and how they should be admitted into the system. We need help designing or reviewing an evidence model that can handle: - authoritative sources; - sanctions lists; - public scam reports; - community reports; - OSINT findings; - phishing/drainer intelligence; - ransomware intelligence; - exploit/hack intelligence; - blockchain labels; - commercial/provider labels; - manual analyst reviews; - low-confidence social/forum data; - conflicting evidence; - outdated evidence; - chain ambiguity; - source freshness; - attribution quality. The candidate should understand that not every source should directly become a final wallet label. Some evidence should be accepted automatically, while other evidence should remain candidate, contextual, or require manual review. Expected output: - source-confidence framework; - evidence admission policy; - recommendations for accepted/candidate/review/context-only states; - guidance on how to avoid false positives; - guidance on how to preserve provenance and auditability. --- 4. Data Ingestion and Enrichment Strategy Review or help design the strategy for collecting and processing intelligence data. The platform may consume or integrate data from categories such as: - sanctions and regulatory lists; - public blockchain labels; - scam and abuse reports; - phishing and drainer intelligence; - ransomware wallets; - exploit and hack databases; - DeFi protocol data; - token and smart contract risk data; - blockchain data providers; - transaction history APIs; - graph datasets; - open-source intelligence sources; - commercial AML/KYT providers; - community or partner reports. The candidate should be able to advise which data sources are worth prioritizing for MVP and which sources are likely to create noise. We are especially interested in someone who understands the difference between: - high-confidence wallet/entity attribution; - generic URL/domain feeds; - unverified community reports; - official sanctions data; - crypto-native scam/phishing intelligence; - contextual OSINT; - raw blockchain transaction data; - commercial provider labels. Expected output: - prioritized data-source strategy; - MVP ingestion plan; - guidance on source quality and licensing; - recommendations for data freshness and update cadence; - data-quality metrics; - ingestion failure and degraded-coverage handling. --- 5. Blockchain Graph and Exposure Logic The platform needs to reason about wallet relationships, transaction paths, and counterparty exposure. The candidate should help evaluate or design logic for: - transaction graph traversal; - direct vs indirect exposure; - hop distance; - counterparty risk; - source and destination classification; - fund flow analysis; - address clustering; - entity attribution; - UTXO heuristics where applicable; - EVM account behavior; - exchange deposit/withdrawal behavior; - bridge interactions; - mixer exposure; - peel chains; - fan-in/fan-out patterns; - rapid movement of funds; - laundering typologies; - graph-based risk inheritance limits. We do not want a black-box model that simply labels everything risky. We need a practical and explainable approach suitable for an MVP. Expected output: - graph-risk review; - recommendations for safe graph expansion; - direct/indirect exposure rules; - clustering strategy; - limitations and false-positive controls; - future roadmap for more advanced graph analytics. --- 6. Backend and Data Engineering Guidance The candidate should be comfortable reviewing or guiding backend/data engineering work. Relevant areas include: - Python backend services; - API design; - microservice architecture; - PostgreSQL schema design; - Redis/caching; - task queues; - async workers; - ETL pipelines; - data normalization; - data deduplication; - provenance tracking; - audit logs; - batch and real-time processing; - rate-limited external API integrations; - retry logic; - observability; - metrics; - test strategy; - production deployment. The candidate does not need to personally implement every component, but should be capable of reviewing the implementation and telling the team what is correct, what is risky, and what should be changed. Expected output: - backend/data architecture recommendations; - review of critical technical decisions; - implementation priorities; - recommendations for reliability, testing, and observability. --- 7. MVP and Production Readiness Assessment We need a realistic assessment of what is required to launch an MVP. The candidate should help answer: - What is already sufficient? - What is missing? - What must be fixed before production? - What can be postponed? - What is dangerous to launch without? - What level of wallet risk coverage is realistic for MVP? - What data sources are enough for the first release? - What risk categories should be supported first? - What should be manual-review only? - What should be internal-only? - What should be customer-facing? - What infrastructure is required? - What team is required? - How much time is needed to reach MVP? - What are the main technical and product risks? Expected output: - production-readiness assessment; - estimated completion percentage; - MVP launch roadmap; - phased technical plan; - required team/specialist recommendations; - infrastructure/resource estimate. --- Expected Deliverables Depending on the engagement format, expected deliverables may include: 1. Architecture Audit Report - current architecture assessment; - critical risks; - missing components; - recommended improvements. 2. Risk Scoring Review - scoring methodology review; - risk category recommendations; - severity and confidence model; - false-positive prevention strategy. 3. Evidence and Source Confidence Framework - evidence admission policy; - source confidence model; - accepted/candidate/review/context-only states; - provenance and auditability recommendations. 4. Data Source and Enrichment Strategy - recommended MVP data sources; - source prioritization; - ingestion strategy; - source-quality metrics; - update cadence recommendations. 5. On-Chain Exposure and Graph Logic Review - direct/indirect exposure rules; - hop-distance handling; - address/entity clustering recommendations; - graph-risk propagation limits. 6. MVP Roadmap - 30/60/90-day implementation plan; - engineering priorities; - must-have vs nice-to-have features; - production-readiness checklist. 7. Team and Resource Plan - required specialists; - estimated workload; - infrastructure/resource needs; - implementation sequencing. 8. Optional Hands-On Contribution - backend implementation; - data pipeline implementation; - schema review; - risk-engine implementation; - API review; - testing and observability improvements. --- Required Experience The ideal candidate should have experience in several of the following areas: Crypto AML / KYT / Compliance Infrastructure - AML/KYT platform development; - wallet screening systems; - transaction monitoring systems; - crypto compliance tools; - blockchain intelligence platforms; - blockchain forensics systems; - address risk scoring; - suspicious activity detection; - sanctions screening; - financial crime risk in crypto; - exposure analysis; - on-chain investigation tooling. Blockchain Analytics - EVM transaction analysis; - Bitcoin/UTXO transaction analysis; - transaction graph analysis; - wallet behavior analysis; - address clustering; - entity attribution; - exchange/service identification; - counterparty risk; - bridge interactions; - mixer/tumbler exposure; - laundering typologies; - scam/phishing/ransomware wallet analysis; - blockchain data provider integrations. Backend / Data Engineering - backend architecture; - API architecture; - microservices; - Python; - FastAPI or similar frameworks; - PostgreSQL; - Redis; - queues/workers; - ETL pipelines; - data ingestion; - data normalization; - schema design; - data provenance; - audit logs; - integration with third-party APIs; - rate limiting; - retries and fault tolerance; - monitoring and observability. Risk and Evidence Modeling - risk scoring; - confidence scoring; - evidence provenance; - source reliability; - false-positive reduction; - severity classification; - manual review workflows; - explainable risk output; - customer-facing risk recommendations; - compliance-sensitive wording. --- Strong Plus Experience with or strong understanding of systems, tools, datasets, or companies such as: - Chainalysis; - TRM Labs; - Elliptic; - Merkle Science; - Crystal Intelligence; - Scorechain; - AMLBot; - Arkham; - Breadcrumbs; - GraphSense; - BlockSci; - Dune; - Flipside; - BigQuery blockchain datasets; - Forta; - GoPlus; - ScamSniffer; - ChainAbuse; - OpenSanctions; - OFAC data; - DeFiLlama; - blockchain labeling datasets; - transaction graph databases; - Neo4j or similar graph databases. Prior employment at one of these companies is not required, but experience building comparable systems is highly relevant. --- Technical Skills We Are Looking For Relevant skills include: - Blockchain; - Cryptocurrency; - Blockchain Analytics; - Blockchain Forensics; - Crypto AML; - KYT; - KYC/AML; - Transaction Monitoring; - Wallet Screening; - Risk Scoring; - Fraud Detection; - Sanctions Screening; - OSINT; - Cyber Threat Intelligence; - Backend Development; - Software Architecture; - System Architecture; - Data Engineering; - ETL Pipelines; - API Development; - Python; - FastAPI; - PostgreSQL; - Redis; - Microservices; - Docker; - Graph Databases; - Neo4j; - BigQuery; - Data Modeling; - Data Integration; - Third-Party API Integration; - Financial Crime Technology; - Compliance Technology. --- What We Are NOT Looking For Please do not apply if your experience is mainly limited to one of the following without relevant backend/data/platform experience: - only Solidity smart contract development; - only NFT projects; - only token launches; - only trading bots; - only crypto trading; - only manual AML investigations; - only compliance operations; - only KYC document verification; - only frontend development; - only general web scraping; - only academic ML without production backend/data systems; - only using Chainalysis/TRM/Elliptic as an end-user without building related systems. We value AML/compliance knowledge, but this role is primarily technical. --- Initial Scope of Work The first engagement can be structured as an audit and architecture review. Phase 1: Discovery and Review - Review current technical documentation. - Review high-level architecture. - Review data flow. - Review wallet analysis flow. - Review risk scoring assumptions. - Review source/enrichment strategy. - Review backend/data pipeline approach. - Identify production risks. Phase 2: Technical Assessment - Assess architecture maturity. - Identify missing components. - Review evidence model. - Review source confidence model. - Review graph/exposure logic. - Review API and backend design. - Review database/data model assumptions. - Assess scalability and reliability. Phase 3: Recommendations - Provide architecture recommendations. - Provide MVP risk-scoring recommendations. - Provide evidence/source-confidence recommendations. - Provide data-source prioritization. - Provide production-readiness checklist. - Provide 30/60/90-day roadmap. - Provide task decomposition for engineers. Phase 4: Optional Hands-On Support Depending on fit and availability, the candidate may also help with: - backend implementation; - risk-engine implementation; - data pipeline improvements; - schema improvements; - API review; - testing strategy; - technical task definition; - developer mentoring; - code review.