Senior Machine Learning and RAG Engineer

Alex Silverman

SENIOR MACHINE LEARNING ENGINEER

Fort Worth, TX 76110 848-***-**** ***************@*****.*** LinkedIn Professional Summary

Senior AI/ML Engineer skilled in designing enterprise-scale machine learning systems, agentic AI platforms, and RAG pipelines to solve complex business challenges. Experienced in end-to-end ML and Generative AI workflows using TensorFlow, PyTorch, AWS SageMaker, LangGraph, Snowflake, Hugging Face, OpenAI frameworks, and SQL generation agents. Strong background in neural architecture design, NLP optimization, LLM fine-tuning, prompt engineering, retrieval optimization, and MLOps practices, including CI/CD and Kubeflow. Adept at building scalable AI solutions across healthcare, enterprise SaaS, and analytics domains while aligning cross- functional teams through agile development practices. Skills

• AI/ML Methodologies & Frameworks: Large Language Models (LLM), Retrieval- Augmented Generation (RAG), Computer Vision, LoRA (Parameter-Efficient Fine-Tuning), Natural Language Processing (NLP), Generative AI, Support Vector Machines (SVM), AI Agent Frameworks, Medical Image Analysis, Predictive Analytics (Classification/Regression Models), Vector Databases, Deep Learning, LangChain (LLM Orchestration), Transformers

(Hugging Face), Image Processing & Enhancement

• Core Languages & Scripting: Python, R, Java, C++, C#, TypeScript

• Model Development Tools & Libraries: PyTorch, Scikit-Learn, Keras, TensorFlow, OpenCV, Matplotlib, PySpark

• Data Engineering & Analytics: Pandas, NumPy, Dask, Spark, Data Visualization

• Cloud Computing & Distributed Systems: AWS services, Google Cloud, Azure, Hadoop, HBase

• Model Deployment & API Services: Docker, Kubernetes, Flask, FastAPI, TensorFlow Serving

• MLOps & Workflow Automation: Jenkins, Git, MLflow, Airflow, Kubernetes

• Data Pipeline Architecture: SQL, MongoDB, Apache Spark, Kafka Experience

Senior Machine Learning Engineer FuturHealth Apr 2022 – Present

• Architected an enterprise-grade multi-agent RAG platform using LangGraph and LangChain, enabling natural language querying of clinical datasets and improving retrieval accuracy for healthcare users.

• Built SQL-generation agents that translated provider questions into optimized Snowflake SQL with RBAC enforcement, domain-specific logic, and secure query execution.

• Developed MCP-based integrations to provide secure, structured access to healthcare data systems across EHR and analytics platforms.

• Designed PromptQL-driven workflows to improve context grounding, reduce hallucinations, and enhance reliability in clinical decision support tools.

• Implemented asynchronous FastAPI services for real-time query routing, background job execution, and scalable inference across production AI workflows.

• Created automated data visualization pipelines using Plotly to dynamically generate charts, KPIs, and analytical insights from query outputs.

• Defined reusable healthcare domain schemas using JSON configurations, enabling scalable agent onboarding without changes to the core orchestration layer.

• Led HIPAA-compliant system design and mentored engineering teams on agent reliability, prompt engineering, RAG optimization, and production AI best practices. Senior Machine Learning Engineer NVIDIA Jun 2017 – Apr 2022

• Designed and developed distributed machine learning pipelines for large-scale AI workloads, supporting model training, evaluation, feature processing, and production deployment across high-performance environments.

• Built embedding-based vector search and retrieval systems using FAISS to enable low- latency semantic search, document retrieval, and similarity matching across large-scale datasets.

• Developed LLM-powered augmentation workflows for semantic query expansion, contextual ranking, retrieval optimization, and improved relevance in AI search and recommendation systems.

• Optimized model inference pipelines using TensorFlow Serving and ONNX Runtime, improving model serving performance, resource utilization, and deployment efficiency.

• Integrated real-time data streaming architectures using Apache Kafka and Apache Spark for feature generation, event processing, analytics, and machine learning data pipelines.

• Containerized and deployed machine learning services with Docker and Kubernetes, improving scalability, fault tolerance, service reliability, and production maintainability.

• Conducted A/B testing, offline model evaluation, performance benchmarking, and error analysis to improve AI-driven product performance and user engagement.

• Contributed to internal MLOps and LLM engineering frameworks for experiment tracking, model evaluation, prompt testing, deployment automation, and continuous model improvement.

Data Scientist Code.org Jun 2015 – May 2017

• Designed and developed scalable educational technology platforms and data-driven learning systems supporting millions of students and educators worldwide, improving accessibility, engagement, and personalized computer science learning experiences.

• Built and optimized machine learning and analytics pipelines to analyze student interactions, learning patterns, and platform usage data, enabling data-informed improvements to curriculum delivery, student outcomes, and teacher support tools.

• Developed backend services, APIs, and cloud-based applications powering interactive coding environments, online courses, assessment systems, and content management workflows while ensuring reliability, scalability, and high performance.

• Collaborated with curriculum designers, educators, product managers, and engineering teams to deliver AI-enhanced learning solutions, automate educational workflows, and improve user experiences across web-based computer science education platforms. Education

UCLA, Bachelor’s Degree in Computational Science 2011 - 2015

Contact this candidate