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

I am an AI & Automation Engineer with 2+ years of experience building GenAI and LLM-based agentic systems to automate document processing and internal workflows. I specialize in Python, AWS (Bedrock), and OpenAI APIs, with hands-on work in prompt engineering, retrieval-augmented generation, and tool invocation using LangChain and LangGraph. I have designed and deployed GenAI solutions that improved accuracy and efficiency while reducing failures. I collaborate with cross-functional teams to translate business requirements into production-grade GenAI solutions, deploying services with Docker, Kubernetes, and CI/CD in production, and optimizing for accuracy, latency, and cost through experimentation and hyperparameter tuning. In my roles, I led retrieval optimization efforts and built end-to-end AI services, including RAG pipelines with FAISS/Pinecone and multi-step agent workflows. I have experience deploying AI systems on AWS and leveraging OpenAI APIs, Bedrock, and transformer fine-tuning (PEFT/LoRA) on domain data. I am passionate about turning complex business problems into reliable GenAI solutions that drive adoption across teams.…I am an AI & Automation Engineer with 2+ years of experience building GenAI and LLM-based agentic systems to automate document processing and internal workflows. I specialize in Python, AWS (Bedrock), and OpenAI APIs, with hands-on work in prompt engineering, retrieval-augmented generation, and tool invocation using LangChain and LangGraph. I have designed and deployed GenAI solutions that improved accuracy and efficiency while reducing failures. I collaborate with cross-functional teams to translate business requirements into production-grade GenAI solutions, deploying services with Docker, Kubernetes, and CI/CD in production, and optimizing for accuracy, latency, and cost through experimentation and hyperparameter tuning. In my roles, I led retrieval optimization efforts and built end-to-end AI services, including RAG pipelines with FAISS/Pinecone and multi-step agent workflows. I have experience deploying AI systems on AWS and leveraging OpenAI APIs, Bedrock, and transformer fine-tuning (PEFT/LoRA) on domain data. I am passionate about turning complex business problems into reliable GenAI solutions that drive adoption across teams.

Sabetha Sheenu Soosai

AI Engineer, Data Scientist, DevOps Developer, +1





I am an AI & Automation Engineer with 2+ years of experience building GenAI and LLM-based agentic systems to automate document processing and internal workflows. I specialize in Python, AWS (Bedrock), and OpenAI APIs, with hands-on work in prompt engineering, retrieval-augmented generation, and tool invocation using LangChain and LangGraph. I have designed and deployed GenAI solutions that improved accuracy and efficiency while reducing failures. I collaborate with cross-functional teams to translate business requirements into production-grade GenAI solutions, deploying services with Docker, Kubernetes, and CI/CD in production, and optimizing for accuracy, latency, and cost through experimentation and hyperparameter tuning. In my roles, I led retrieval optimization efforts and built end-to-end AI services, including RAG pipelines with FAISS/Pinecone and multi-step agent workflows. I have experience deploying AI systems on AWS and leveraging OpenAI APIs, Bedrock, and transformer fine-tuning (PEFT/LoRA) on domain data. I am passionate about turning complex business problems into reliable GenAI solutions that drive adoption across teams.…I am an AI & Automation Engineer with 2+ years of experience building GenAI and LLM-based agentic systems to automate document processing and internal workflows. I specialize in Python, AWS (Bedrock), and OpenAI APIs, with hands-on work in prompt engineering, retrieval-augmented generation, and tool invocation using LangChain and LangGraph. I have designed and deployed GenAI solutions that improved accuracy and efficiency while reducing failures. I collaborate with cross-functional teams to translate business requirements into production-grade GenAI solutions, deploying services with Docker, Kubernetes, and CI/CD in production, and optimizing for accuracy, latency, and cost through experimentation and hyperparameter tuning. In my roles, I led retrieval optimization efforts and built end-to-end AI services, including RAG pipelines with FAISS/Pinecone and multi-step agent workflows. I have experience deploying AI systems on AWS and leveraging OpenAI APIs, Bedrock, and transformer fine-tuning (PEFT/LoRA) on domain data. I am passionate about turning complex business problems into reliable GenAI solutions that drive adoption across teams.

Available to hire

I am an AI & Automation Engineer with 2+ years of experience building GenAI and LLM-based agentic systems to automate document processing and internal workflows. I specialize in Python, AWS (Bedrock), and OpenAI APIs, with hands-on work in prompt engineering, retrieval-augmented generation, and tool invocation using LangChain and LangGraph. I have designed and deployed GenAI solutions that improved accuracy and efficiency while reducing failures. I collaborate with cross-functional teams to translate business requirements into production-grade GenAI solutions, deploying services with Docker, Kubernetes, and CI/CD in production, and optimizing for accuracy, latency, and cost through experimentation and hyperparameter tuning.

In my roles, I led retrieval optimization efforts and built end-to-end AI services, including RAG pipelines with FAISS/Pinecone and multi-step agent workflows. I have experience deploying AI systems on AWS and leveraging OpenAI APIs, Bedrock, and transformer fine-tuning (PEFT/LoRA) on domain data. I am passionate about turning complex business problems into reliable GenAI solutions that drive adoption across teams.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Language

English

Fluent

Work Experience

Software Development Engineer II (AI & Automation) at Arcadia

October 1, 2023 - Present

Designed and developed GenAI agentic systems using LLMs to automate document processing and internal business workflows. Built and deployed LLM applications on AWS using Amazon Bedrock and OpenAI APIs, implementing RAG pipelines with FAISS/Pinecone and serving them via FastAPI. Implemented agent-based workflows using LangChain and LangGraph for multi-step reasoning, tool invocation, and orchestration. Led prompt engineering and retrieval optimization, reducing document extraction failures by 80%. Performed data preprocessing, normalization, and contextual chunking to improve retrieval accuracy and response consistency. Conducted experimentation, hyperparameter tuning, and model evaluation to optimize accuracy, latency, and cost. Deployed and operated AI services using Docker, Kubernetes, and CI/CD pipelines in production environments. Fine-tuned transformer-based LLMs using Hugging Face (PEFT / LoRA) on domain-specific datasets to improve accuracy and robustness of GenAI applications.

Data Science Intern at Vlog Innovations

September 1, 2022 - December 1, 2022

Queried and optimized large-scale datasets using SQL, improving data retrieval efficiency by 25%. Designed and delivered interactive dashboards using Tableau and Power BI, reducing reporting turnaround time by 40% and enabling faster decision-making. Developed and deployed NLP-based applications using Streamlit, improving team productivity by 30% and cutting deployment time by 50%.