Overview

Multiple positions available. 1. Architect and implement AI-powered backend systems for analytics and report generation, utilizing large language model (LLM) pipelines for natural language query processing and translation across SQL and openCypher. 2. Design and implement intent-driven query routing and stateful multi-turn execution logic to enable accurate filtering, aggregation, and contextual query refinement within conversational systems. 3. Develop dynamic prompt and context retrieval pipelines using semantic search and embedding-based retrieval techniques, combined with ranking methods to improve system accuracy and preserve business logic consistency. 4. Develop and optimize data pipelines using Python and SQL to support high-throughput data processing, query translation, and validation workflows in low-latency environments. 5. Design and implement backend services based on Model Context Protocol (MCP) to expose structured database tools and enable deterministic query execution across data systems. 6. Develop and implement machine learning models using Python and PySpark on Databricks to support validation, scoring, and optimization of analytics systems. 7. Apply statistical and machine learning techniques across the full lifecycle, including data preprocessing, feature engineering, model development, validation, and deployment, and perform Bayesian hyperparameter optimization to improve model performance, utilizing mlflow for experiment tracking and Git for version control. 8. Design and implement systems for document processing and workflow orchestration using LangChain and LangGraph within production environments. 9. Design and deploy scalable backend system components, including data processing and caching layers using Python and SQL, to support low-latency and high-throughput analytics workflows. 10. Design and implement distributed system optimizations, including caching strategies and event-driven processing using technologies such as Redis and Kafka, to ensure system reliability and performance. 11. Develop data validation and quality assurance mechanisms using machine learning models and statistical techniques to ensure accuracy, consistency, and integrity of data-driven systems. 12. Design and implement identity verification and fraud risk scoring systems by applying patterns from end-to-end ID verification and KYC fraud models, utilizing Python, TensorFlow, AWS, OpenCV, and CUDA, and machine learning libraries such as NumPy, Scikit-learn, Keras, and Pandas to develop, validate, and optimize data quality and risk-scoring mechanisms. Experience must include: a. Implementing intent-driven query routing and stateful multi-turn execution logic to enable accurate filtering, aggregation, and contextual query refinement within chatbot systems. b. Developing dynamic system prompt retrieval pipelines using semantic search and embedding-based retrieval techniques. c. Designing, developing and optimizing AI-powered backend systems, including large language model (LLM) pipelines for natural language query processing and response generation. d. Developing and optimizing data pipelines using Python and SQL. e. Developing Model Context Protocol (MCP) backends to expose structured database tools for deterministic execution. f. Developing and implementing machine learning models using Python, PySpark on Databricks. g. Applying Bayesian Hyperparameter optimization techniques to tune and improve model performance. h. Designing and building prototype systems for document processing and chargeback resolution using LangChain and LangGraph. i. Applying Statistical and machine learning techniques including data preprocessing, feature engineering, model development, validation, and production deployment utilizing mlflow for experiment tracking and Git for Version control. This position requires a Master's (or foreign educ. equiv.) Degree in Computer Science, Computer Engineering, Electrical Engineering, or a related field plus one (1)