Duties: Design, deploy, and manage prompt-based models on LLMs for various NLP tasks in the financial services domain. Conduct research on prompt engineering techniques to improve the performance of prompt-based models within the financial services field, exploring and utilizing LLM orchestration and agentic AI libraries. Collaborate with cross-functional teams to identify requirements and develop solutions to meet business needs within the organization. Build and maintain data pipelines and data processing workflows for prompt engineering on LLMs utilizing cloud services for scalability and efficiency. Develop and maintain tools and frameworks for prompt-based model training, evaluation, and optimization. Optimize prompt engineering pipelines for external entity extraction, improving accuracy and reducing manual validation efforts. Develop LLM-enhanced retrieval-augmented generation systems, integrating structured data such as tables and images into financial document processing workflows. Lead model evaluation and enhancement efforts by applying both supervised and unsupervised techniques, ensuring high precision in financial data reconciliations and entity validation. Design and implement NLP-powered reconciliation frameworks to streamline financial break resolution processes. Deploy explainable AI techniques for LLM-based decision- making processes in financial applications, ensuring regulatory compliance and transparency. Implement scalable and generic ML frameworks leveraging search-based architectures to optimize reconciliation and regulatory processes. Develop and deploy enhanced OCR models to improve entity recognition and document parsing while preserving structural integrity.
QUALIFICATIONS:
Minimum education and experience required: Master's degree in Computer Engineering, Electrical Engineering, Computer Science, Data Science, or related field of study plus 3 years of experience in the job offered or as Applied AI/ML Associate, Software Engineer, or related occupation.
Skills Required: This position requires experience with the following: Performing data manipulation, structuring, design flow, and query optimization using SQL and Python; Processing large data sets with PySpark and SQL to perform Exploratory Data Analysis for model improvements, feature engineering, and the analyses; Explaining performance of models based on statistical characteristics; Running the procedures for the P-value approach to hypothesis testing; Estimating the distribution of sample statistics using sampling techniques such as bootstrapping; Developing and applying advanced machine learning techniques including ARIMA, SARIMA, Regression techniques, Classification methods, Ensemble Methods, Clustering, Dimensionality Reduction, and NLP, including TF-IDF, embeddings, and fuzzy matching, Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, Naive Bayes, K-Nearest Neighbors, and Neural Network, and comparing results to select the best model; Evaluating and interpreting models using tools such as Shapley Analysis; Programming in Python and SQL utilizing frameworks and libraries including Scikit-Learn, and PyTorch or TensorFlow; Developing pipelines for data manipulation and feature engineering using big data technologies including Apache Spark and tools including Jupyter Lab and Tableau; Shell and Bash scripting, for operating systems including Windows and Linux, and version control systems such as GitHub or Bitbucket; Designing and developing neural network models such as RNN, LSTM, or CNN using frameworks such as Keras, Tensorflow, or Pytorch.
Job Location: 3223 Hanover St, Palo Alto, CA 94304.
Full-Time. Salary: $185,900 - $260,000 per year.