AI/ML Engineer with 3+ years of experience designing, building, and deploying scalable machine learning, Generative AI, and LLM-powered solutions across enterprise environments. Expertise in Retrieval-Augmented Generatio…
AI/ML Engineer with 3+ years of experience designing, building, and deploying scalable machine learning, Generative AI, and LLM-powered solutions across enterprise environments. Expertise in Retrieval-Augmented Generation (RAG), NLP, prompt engineering, agentic AI, model deployment, and end-to-end MLOps pipelines using FastAPI, Docker, Kubernetes, MLflow, and cloud platforms including AWS and Azure. Strong background in large-scale data processing, vector search, semantic retrieval, and healthcare AI solutions, delivering production-grade systems that improve operational efficiency, automate workflows, and support data-driven business decisions.
Developed AI-driven healthcare automation solutions using LLMs, RAG pipelines, and LangChain by analyzing manual workflows, reducing operational effort by 30% across document-heavy clinical processes.
Engineered end-to-end RAG systems by processing 100K+ clinical documents, implementing chunking, embeddings, FAISS/Pinecone vector storage, and hybrid search for faster semantic retrieval.
Improved response quality by applying prompt chaining, function calling, LLM guardrails, and hallucination reduction techniques, increasing healthcare-specific response consistency and accuracy by 20%.
Built scalable backend microservices using FastAPI, REST APIs, OAuth2, JWT, and Swagger/OpenAPI, supporting seamless AI integration across applications handling 1K+ daily requests.
Managed production deployments using Docker, Kubernetes, Azure ML, and Terraform while implementing CI/CD pipelines, maintaining 99% uptime across scalable enterprise AI environments.
Optimized inference pipelines through embedding strategy tuning, context window optimization, and retrieval re-ranking, reducing latency by 25% while improving relevance and response precision.
Implemented MLflow, model monitoring, Prometheus, and Grafana dashboards for experiment tracking, model observability, and production issue detection across deployed AI systems.
Developed AI-driven healthcare automation solutions using LLMs, RAG pipelines, and LangChain by analyzing manual workflows, reducing operational effort by 30% across document-heavy clinical processes., Engineered end-to-end RAG systems by processing 100K+ clinical documents, implementing chunking, embeddings, FAISS/Pinecone vector storage, and hybrid search for faster semantic retrieval., Improved response quality by applying prompt chaining, function calling, LLM guardrails, and hallucination reduction techniques, increasing healthcare-specific response consistency and accuracy by 20%., Built scalable backend microservices using FastAPI, REST APIs, OAuth2, JWT, and Swagger/OpenAPI, supporting seamless AI integration across applications handling 1K+ daily requests., Managed production deployments using Docker, Kubernetes, Azure ML, and Terraform while implementing CI/CD pipelines, maintaining 99% uptime across scalable enterprise AI environments., Optimized inference pipelines through embedding strategy tuning, context window optimization, and retrieval re-ranking, reducing latency by 25% while improving relevance and response precision., Implemented MLflow, model monitoring, Prometheus, and Grafana dashboards for experiment tracking, model observability, and production issue detection across deployed AI systems.
Designed and deployed machine learning models for document classification, automation, and NLP workflows using structured and unstructured datasets, improving model prediction accuracy by 25%.
Built scalable ETL and feature engineering pipelines processing 10M+ records using Python, SQL, Airflow, and Spark, improving data quality and operational efficiency significantly.
Enhanced model performance by applying cross-validation, hyperparameter tuning, MLflow experiment tracking, and drift detection, reducing inference time by 30% while maintaining model accuracy.
Developed NLP and document intelligence solutions using transformers, entity extraction, and semantic search techniques, improving precision and recall rates by 20% across enterprise workflows.
Deployed ML models using Docker, AWS SageMaker, Kubernetes, and CI/CD pipelines, supporting 5+ production applications with stable performance and enterprise-grade scalability.
Improved preprocessing workflows using automation, validation frameworks, and data transformation optimization, reducing overall processing time by 25% and improving downstream model reliability.
Collaborated with cross-functional teams and stakeholders to translate business requirements into production ML solutions, delivering 3+ successful POCs with measurable cost savings.
Designed and deployed machine learning models for document classification, automation, and NLP workflows using structured and unstructured datasets, improving model prediction accuracy by 25%., Built scalable ETL and feature engineering pipelines processing 10M+ records using Python, SQL, Airflow, and Spark, improving data quality and operational efficiency significantly., Enhanced model performance by applying cross-validation, hyperparameter tuning, MLflow experiment tracking, and drift detection, reducing inference time by 30% while maintaining model accuracy., Developed NLP and document intelligence solutions using transformers, entity extraction, and semantic search techniques, improving precision and recall rates by 20% across enterprise workflows., Deployed ML models using Docker, AWS SageMaker, Kubernetes, and CI/CD pipelines, supporting 5+ production applications with stable performance and enterprise-grade scalability., Improved preprocessing workflows using automation, validation frameworks, and data transformation optimization, reducing overall processing time by 25% and improving downstream model reliability., Collaborated with cross-functional teams and stakeholders to translate business requirements into production ML solutions, delivering 3+ successful POCs with measurable cost savings.
The AI-first Recruitment Operating System that unifies and automates the entire hiring lifecycle for modern enterprises worldwide.
Dr Job FZ LLC. 2026 © All Rights Reserved
