Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

Senior AI Engineer with 8+ years spanning data engineering, machine learning model training, and Generative AI. Proven experience at Amazon and Salesforce, plus enterprise consulting work building production-grade LLM applications, agentic workflows, and scalable RAG pipelines. Specializes in robust LLM application architectures (LangGraph/CrewsAI-style multi-agent systems), Model Context Protocol (MCP) integrations, and hybrid search/GraphRAG approaches—paired with full-stack engineering to deliver reliable AI products end-to-end.…Senior AI Engineer with 8+ years spanning data engineering, machine learning model training, and Generative AI. Proven experience at Amazon and Salesforce, plus enterprise consulting work building production-grade LLM applications, agentic workflows, and scalable RAG pipelines. Specializes in robust LLM application architectures (LangGraph/CrewsAI-style multi-agent systems), Model Context Protocol (MCP) integrations, and hybrid search/GraphRAG approaches—paired with full-stack engineering to deliver reliable AI products end-to-end.

Kevin Weithers

AI Engineer, Data Scientist, Software Engineer, +1





Senior AI Engineer with 8+ years spanning data engineering, machine learning model training, and Generative AI. Proven experience at Amazon and Salesforce, plus enterprise consulting work building production-grade LLM applications, agentic workflows, and scalable RAG pipelines. Specializes in robust LLM application architectures (LangGraph/CrewsAI-style multi-agent systems), Model Context Protocol (MCP) integrations, and hybrid search/GraphRAG approaches—paired with full-stack engineering to deliver reliable AI products end-to-end.…Senior AI Engineer with 8+ years spanning data engineering, machine learning model training, and Generative AI. Proven experience at Amazon and Salesforce, plus enterprise consulting work building production-grade LLM applications, agentic workflows, and scalable RAG pipelines. Specializes in robust LLM application architectures (LangGraph/CrewsAI-style multi-agent systems), Model Context Protocol (MCP) integrations, and hybrid search/GraphRAG approaches—paired with full-stack engineering to deliver reliable AI products end-to-end.

Available to hire

Senior AI Engineer with 8+ years spanning data engineering, machine learning model training, and Generative AI. Proven experience at Amazon and Salesforce, plus enterprise consulting work building production-grade LLM applications, agentic workflows, and scalable RAG pipelines.

Specializes in robust LLM application architectures (LangGraph/CrewsAI-style multi-agent systems), Model Context Protocol (MCP) integrations, and hybrid search/GraphRAG approaches—paired with full-stack engineering to deliver reliable AI products end-to-end.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Work Experience

Senior AI Engineer at Cognizant

June 1, 2024 - Present

Architected production-grade multi-agent systems and advanced RAG platforms to automate enterprise workflows across financial compliance auditing, healthcare data retrieval, and e-commerce support escalation. Led enterprise-grade Agentic AI and RAG implementations including GraphRAG and Hybrid Search for Fortune 500 clients. Built full-stack GenAI applications using AWS Bedrock/Azure OpenAI with React/TypeScript and FastAPI/Python backends. Implemented multi-agent workflows using LangGraph and CrewAI for autonomous tool calling and multi-step reasoning. Integrated external data sources securely via Model Context Protocol (MCP), establishing standardized connections to proprietary databases while mitigating prompt-injection risks. Developed custom system prompts and few-shot approaches to reduce hallucinations and improve reliability.

Senior Machine Learning Engineer (SDE III) at Amazon

July 1, 2021 - June 1, 2024

Developed and deployed large-scale ML models using PyTorch/TensorFlow in the AWS SageMaker ecosystem, processing terabytes of customer data to improve recommendation systems. Optimized LLM inference latency and reduced compute costs by 30% using quantization (AWQ/GPTQ) and efficient serving with vLLM and TensorRT-LLM. Collaborated with data scientists and product managers to translate requirements into scalable ML architectures. Mentored engineers and established CI/CD and MLOps best practices for ML deployment automation. Applied deep learning over large sequential datasets to improve recommendation click-through rates by 15%.

Data Engineer at Salesforce

April 1, 2018 - July 1, 2020

Architected and maintained ETL pipelines using Apache Spark and Python to process large volumes of CRM data for downstream analytics and ML. Modeled and governed data using dbt to ensure modularity and high-quality inputs. Designed and optimized relational and NoSQL schemas for high-performance analytics and reporting. Automated data quality checks and monitoring, reducing data downtime by 25%. Partnered with data science teams to operationalize ML workflows from raw storage to training environments.

Data Scientist at Enova International

May 1, 2016 - April 1, 2018

Built predictive credit-risk models with scikit-learn and Pandas to optimize lending strategy, increasing safe loan approvals by 10%. Performed EDA and A/B testing to derive actionable insights and improve customer conversion rates. Engineered scalable data processing pipelines and feature engineering for models including Random Forest and XGBoost. Applied early NLP techniques to extract sentiment and insights from unstructured customer support interactions.