Pavel Vasilyev

LLM Engineer / AI Infrastructure Specialist
Jerusalem, Israel
+972-54-343-1123

Profile

LLM engineer with 14 years ML/NLP experience and 3 years specializing in production language model systems. Expert in LLM workflows, safety guardrails, prompt engineering, and scaling generative AI infrastructure. Strong functional programming background (Clojure, Elixir, Rust) with production Python, Java, and R experience. MSc Computational Linguistics, BSc Nuclear Physics.

Experience

Co-Founder & Technical Lead

Fintilligence Remote 2024-08 – 2024-12 founder
Built fintech analytics platform for detecting asymmetric information flow using PIN/VPIN market microstructure measures.
Architecture
  • Built full-stack fintech analytics platform for detecting asymmetric information flow in financial markets
  • Implemented PIN/VPIN (Probability of Informed Trading/Volume-Synchronized PIN) measures for market microstructure analysis
Engineering
  • Designed and deployed data acquisition pipelines processing Level 2 market data (order book, bid-ask spreads, trade flow)
  • Managed PostgreSQL database architecture for high-frequency trade and quote data storage
  • Built investment advisory system highlighting potential information asymmetries and trading opportunities
Leadership
  • Coordinated small team (3 people) across research, development, and UI design
Languages: Python
Frameworks: Flask, pandas
Infrastructure: AWS EC2, AWS S3

CTO (Contract)

LevEhat NGO Remote 2024-03 – 2024-07 contract
Led technical operations for civic tech nonprofit, managing cloud migration and platform development.
Leadership
  • Led technical operations for civic tech nonprofit focused on volunteer coordination
  • Coordinated UI designers and developers (team of 5) for volunteer management platform
  • Established development priorities and technical roadmap for platform evolution
Engineering
  • Managed migration from Google Cloud Platform to AWS infrastructure (cost optimization)
  • Oversaw database architecture for volunteer tracking, task assignment, and activity logging
Languages: Python
Infrastructure: AWS EC2, AWS S3

AI Architect (Contract)

Stamina AI Remote 2023-01 – 2023-12 contract
Architected and deployed one of the early therapeutic chatbot systems for mental health support using OpenAI GPT-3.5/4.
Architecture
  • Architected and deployed one of the early therapeutic chatbot systems for mental health support
  • Built complete LLM pipeline: prompt engineering, context management, response generation, safety guardrails
  • Designed conversation state management and session handling for therapeutic context
Engineering
  • Integrated OpenAI GPT-3.5/4 APIs with custom safety layers and content filtering
  • Set up production infrastructure: API gateway, load balancing, monitoring, logging
  • Implemented usage analytics and conversation quality monitoring dashboards
Leadership
  • Coordinated with consulting psychotherapists to ensure clinical appropriateness of responses
  • Managed small dev team (2-3 developers) implementing mobile and web interfaces
Languages: Python
Frameworks: Flask, OpenAI API, GPT-3.5, GPT-4
Infrastructure: AWS, Docker, Kubernetes

Independent Consultant

Various Clients Remote 2022-01 – 2023-01 consulting
ML and data consulting for various clients.
Consulting
  • ML and data consulting for various clients: model development, pipeline architecture, statistical analysis
  • Projects included: time-series forecasting, text classification, data pipeline optimization
Languages: Python

Senior Researcher

Spring Research Remote 2020-01 – 2021-12 full-time
ML models for trading signal generation using Level 2 market data and topology-inspired approaches.
Research
  • Developed ML models for trading signal generation using time-series analysis and statistical methods
  • Researched topology-inspired approaches to market microstructure modeling
Engineering
  • Built data pipelines processing Level 2 market data (tick-by-tick, order book, market depth)
  • Implemented backtesting infrastructure for strategy evaluation
  • Collaborated with quantitative research team on experimental high-frequency strategies
Languages: Python
Frameworks: pandas, numpy, scikit-learn
Infrastructure: AWS

Data Scientist

Nestlogic Remote 2019-01 – 2019-12 full-time
Computer vision models for advertising optimization, A/B testing infrastructure, production ML deployment.
Engineering
  • Built computer vision models for advertising creative optimization (image feature extraction)
  • Implemented A/B testing infrastructure using statistical hypothesis testing (t-tests, chi-square)
  • Deployed ML models to production on Google Cloud Platform with Kubernetes
  • Developed analytics dashboards tracking model performance and business KPIs
Languages: Python
Frameworks: PyTorch, OpenCV
Infrastructure: GCP, Kubernetes

Data Scientist

Maverick Medical AI Remote 2018-01 – 2018-12 full-time
Medical NLP system for clinical entity recognition, ontology frameworks, HIPAA-compliant data handling.
Engineering
  • Developed NLP system for medical named entity recognition in clinical text using spaCy and BiLSTM
  • Built medical ontology framework for standardizing terminology across different hospital systems
  • Created decision support tools for clinical workflows highlighting critical findings
  • Worked within HIPAA compliance requirements for healthcare data
Languages: Python, R
Frameworks: spaCy, PyTorch, Flask

Full-Stack Engineer

Athena Portfolio Solutions Remote 2017-01 – 2017-12 full-time
Full-stack financial NLP platform extracting signals from news and SEC filings using knowledge graphs.
Engineering
  • Built full-stack financial NLP platform extracting signals from news and SEC filings
  • Developed Java backend services for data processing and entity recognition
  • Implemented entity linking system connecting market events to portfolio positions
  • Built sentiment analysis models for earnings calls and analyst reports
  • Created knowledge graph of financial entities (companies, people, events, relationships)
Languages: Java, Python, R
Frameworks: spaCy, NLTK, scikit-learn

Technical Tutor (Intermittent)

Private Practice Remote 2017-01 – present intermittent
Mathematics, statistics, programming, and computational linguistics tutoring.
Education
  • Mathematics, statistics, programming, and computational linguistics tutoring
  • Students: high school through graduate level, plus professional colleagues
  • Peak activity during 2020 pandemic period

Education

MSc Computational Linguistics
Russian State University for the Humanities (RSUH) • Moscow, Russia • 2016 (2011-2016 (5 years))
Statistical NLP, Machine Translation, Information Extraction
BSc Nuclear Physics
Czech Technical University • Prague, Czech Republic • 2011 (2009-2011)
Mathematical Modeling, Statistical Analysis, Computational Physics

Technical Skills

⚡ LLM Engineering Specialist
Production LLM Systems
3 years production LLM systems (2023-present)
APIs & Models: OpenAI API (GPT-3.5/4) • Anthropic Claude
Workflows: Prompt engineering and optimization • RAG (Retrieval Augmented Generation) pipelines • Context window management • Token optimization • Streaming responses
Safety & Guardrails: Safety guardrails and content filtering • Output validation and moderation • Adversarial prompt detection • PII scrubbing
Infrastructure: Production LLM deployment • Latency optimization • Cost management • Usage monitoring and analytics • Error handling and fallbacks
Specializations: Therapeutic/healthcare chatbots • Conversational AI • Fine-tuning workflows • Evaluation frameworks
Core Languages
Elixir 2+ years, proficient — Recent production experience, concurrent systems, functional programming, OTP patterns
Rust 2+ years, proficient — Recent production experience, performance-critical systems, systems programming
Clojure 10+ years, expert — Primary language for data science workflows, Jupyter integration, JVM interop, functional data processing
Python 10+ years, expert — ML/AI production, pandas, numpy, scikit-learn, PyTorch, TensorFlow, Keras, spaCy, NLTK, Hugging Face Transformers
SQL 8+ years, advanced — Complex queries, query optimization, database design
ML/AI Frameworks
PyTorch TensorFlow Keras scikit-learn XGBoost LightGBM CatBoost spaCy NLTK Hugging Face Transformers OpenCV PIL
Domain Expertise
Llm Production
Stamina AI • 1 year (2023)
Therapeutic chatbot for mental health • Safety systems and guardrails • Prompt engineering workflows • RAG pipeline implementation • Production LLM deployment
Quantitative Finance
Fintilligence, Spring Research • 2+ years
Level 2 market data processing • PIN/VPIN algorithm implementation • Order flow analysis • Market microstructure modeling • Backtesting infrastructure
Healthcare Ai
Maverick Medical AI • 1 year (2018)
Medical named entity recognition • Clinical terminology standardization • HIPAA-compliant systems • Decision support tools
Financial Nlp
Athena Portfolio Solutions • 1 year (2017)
SEC filings extraction • Knowledge graph construction • Entity linking systems • Sentiment analysis for earnings calls

Languages

Russian native
English fluent
French conversational
German conversational
Czech conversational
Hebrew basic