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

I’m Amena Asar, a Senior AI/ML Engineer who builds production-ready, LLM-powered applications using Python and FastAPI. My work focuses on Retrieval-Augmented Generation (RAG), AI agents, semantic search, and fine-tuning—turning complex models into reliable backend services with clean APIs. I enjoy designing end-to-end systems that connect modern AI tooling (OpenAI, LangChain, LangGraph, Hugging Face, Pinecone) with scalable infrastructure (Docker, AWS, Azure). Alongside core model work, I’ve automated workflows with n8n/Make/Zapier and deliver thoughtful, user-facing integrations that make AI solutions practical for real business needs.…I’m Amena Asar, a Senior AI/ML Engineer who builds production-ready, LLM-powered applications using Python and FastAPI. My work focuses on Retrieval-Augmented Generation (RAG), AI agents, semantic search, and fine-tuning—turning complex models into reliable backend services with clean APIs. I enjoy designing end-to-end systems that connect modern AI tooling (OpenAI, LangChain, LangGraph, Hugging Face, Pinecone) with scalable infrastructure (Docker, AWS, Azure). Alongside core model work, I’ve automated workflows with n8n/Make/Zapier and deliver thoughtful, user-facing integrations that make AI solutions practical for real business needs.

Amena Asar

AI Engineer, Data Scientist, Software Engineer, +4





I’m Amena Asar, a Senior AI/ML Engineer who builds production-ready, LLM-powered applications using Python and FastAPI. My work focuses on Retrieval-Augmented Generation (RAG), AI agents, semantic search, and fine-tuning—turning complex models into reliable backend services with clean APIs. I enjoy designing end-to-end systems that connect modern AI tooling (OpenAI, LangChain, LangGraph, Hugging Face, Pinecone) with scalable infrastructure (Docker, AWS, Azure). Alongside core model work, I’ve automated workflows with n8n/Make/Zapier and deliver thoughtful, user-facing integrations that make AI solutions practical for real business needs.…I’m Amena Asar, a Senior AI/ML Engineer who builds production-ready, LLM-powered applications using Python and FastAPI. My work focuses on Retrieval-Augmented Generation (RAG), AI agents, semantic search, and fine-tuning—turning complex models into reliable backend services with clean APIs. I enjoy designing end-to-end systems that connect modern AI tooling (OpenAI, LangChain, LangGraph, Hugging Face, Pinecone) with scalable infrastructure (Docker, AWS, Azure). Alongside core model work, I’ve automated workflows with n8n/Make/Zapier and deliver thoughtful, user-facing integrations that make AI solutions practical for real business needs.

Next availability:

September 15, 2026

Manalapan Township, United States

I’m Amena Asar, a Senior AI/ML Engineer who builds production-ready, LLM-powered applications using Python and FastAPI. My work focuses on Retrieval-Augmented Generation (RAG), AI agents, semantic search, and fine-tuning—turning complex models into reliable backend services with clean APIs.

I enjoy designing end-to-end systems that connect modern AI tooling (OpenAI, LangChain, LangGraph, Hugging Face, Pinecone) with scalable infrastructure (Docker, AWS, Azure). Alongside core model work, I’ve automated workflows with n8n/Make/Zapier and deliver thoughtful, user-facing integrations that make AI solutions practical for real business needs.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Work Experience

Senior AI/ML Engineer at Advantage Solutions

April 1, 2022 - Present

Engineered AI-powered applications using Python and FastAPI, delivering scalable APIs for intelligent automation and real-time decision support. Developed LLM-driven solutions leveraging OpenAI and Hugging Face models for content generation, summarization, classification, and knowledge retrieval. Built Retrieval-Augmented Generation (RAG) pipelines using LangChain, LangGraph, and Pinecone to enable context-aware search and question-answering. Designed and orchestrated AI agents to execute multi-step workflows and autonomous business processes. Automated enterprise workflows using n8n, Make.com, and Zapier to reduce manual effort and operational bottlenecks. Fine-tuned transformer-based models for domain-specific use cases. Containerized AI services with Docker and deployed scalable solutions on AWS with monitoring and observability via Sentry AI.

Python ML Engineer at Medidata

May 1, 2019 - April 1, 2022

Developed machine learning solutions using Python (Scikit-Learn, TensorFlow, PyTorch) to support predictive analytics and business intelligence initiatives. Built data preprocessing and feature engineering pipelines to improve model performance, reliability, and training efficiency. Designed and deployed RESTful APIs using FastAPI to expose machine learning models for real-time inference and enterprise integration. Implemented NLP solutions for document classification, information extraction, and text analytics across large healthcare datasets. Used Docker and AWS services to deploy and manage ML applications. Collaborated with data scientists and business teams to translate analytical requirements into production-ready ML solutions. Established model monitoring, evaluation, and retraining processes to maintain long-term model performance.

Python Developer at Wells Fargo

September 1, 2016 - May 1, 2019

Developed backend applications and automation solutions using Python to streamline business operations. Designed and implemented RESTful APIs for integration between internal applications, databases, and third-party services. Built reusable Python modules for data processing, validation, reporting, and business workflow automation. Optimized SQL queries, stored procedures, and database operations across Oracle and SQL Server environments. Implemented application security, input validation, exception handling, and logging for stability and compliance. Collaborated across teams to troubleshoot production issues and deliver scalable solutions. Automated build and deployment processes using Jenkins and Docker to improve release efficiency.