Open to opportunities

Charity Pendo

@charitypendo

Message

Senior AI/ML engineer building generative AI and NLP solutions—RAG, LLM deployment, and MLOps for real-world impact.

United States

Message

What I'm looking for

I’m looking to lead end-to-end GenAI/ML products—building RAG and fine-tuned LLM solutions with strong MLOps on AWS/Azure, while partnering with cross-functional teams and keeping compliance and responsible AI at the core.

I’m a Senior AI/ML Engineer specialized in developing and deploying AI-driven solutions with a strong focus on Generative AI, deep learning, and natural language processing (NLP). I build production-ready AI applications using frameworks like LangChain, LlamaIndex, and Semantic Kernel, with hands-on work across GPT-4o-mini, Llama, and LLM fine-tuning.

In my current role at Amazon, I spearheaded a Generative AI platform for automated legal document review using Amazon Bedrock (Claude V2), LangChain, and Pinecone—reducing manual analysis time by 60%. I engineered multi-format ingestion pipelines (PDFs, TIFFs, text) using Textract/Tesseract/Abbyy OCR, built scalable embedding workflows with Amazon Titan Embeddings, and delivered FastAPI-based inference endpoints with Streamlit for non-technical users.

Previously at Cognizant and Accenture, I led architecture for GenAI assistants, intent detection, and NLP extraction systems, improving resolution times by 40% and boosting accuracy by 19% over legacy approaches. I’m especially proud of end-to-end MLOps work (Airflow/SageMaker/MLflow, Docker, Kubernetes, CI/CD) and my commitment to AI Ethics & Compliance—aligning solutions with HIPAA and Responsible AI guidelines.

Experience

Work history, roles, and key accomplishments

Current

Senior AI/ML Engineer

Current

Amazon

Jan 2024 - Present (2 years 3 months)

Spearheaded a generative AI platform for automated legal document review using Amazon Bedrock, LangChain, and Pinecone, reducing manual analysis time by 60%. Built document ingestion and scalable RAG infrastructure, and deployed FastAPI/Streamlit inference on Docker, Kubernetes, and AWS Lambda with full-cycle MLOps.

Lang Chain Pinecone Amazon Titan Embeddings Retrieval Augmented Generation (RAG)fastAPI Docker Kubernetes MLOps

Machine Learning Engineer

Cognizant Technology Solutions

Apr 2021 - Dec 2023 (2 years 8 months)

Architected a generative AI customer support assistant for a top U.S. bank, integrating OpenAI GPT-4 with internal CRM data to improve resolution times by 40%. Developed intent detection with RoBERTa (19% accuracy lift), built an Airflow+SageMaker+MLflow MLOps platform for 12+ models, and mentored junior engineers.

Pinecone RoBERTa Airflow Amazon SageMaker MLFlow SHAP

Machine Learning Engineer

Accenture

Feb 2018 - Mar 2021 (3 years 1 month)

Developed a legal document classification system with BERT for a global law firm, achieving 94% F1 score across multi-label categories. Built contract clause extraction with OCR/Spacy/regex, deployed FastAPI microservices on Azure Kubernetes Service, and implemented drift detection and performance analytics with Databricks and MLflow.

BERT Regex fastAPI Azure Kubernetes Service Databricks MLFlow

ML Engineer / Data Scientist

Infosys

Aug 2015 - Jan 2018 (2 years 5 months)

Built predictive maintenance models for IoT manufacturing clients using LSTM and Random Forest, reducing downtime by 22%. Created anomaly detection pipelines (Isolation Forest, autoencoders) and managed batch/streaming data ingestion with Apache Spark, Kafka, and Snowflake for warehousing and analytics.

Random Forest Isolation Forest Apache Spark Apache Kafka Snowflake Predictive Maintenance Anomaly Detection