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

AI/ML Engineer with 3+ years of experience designing and deploying scalable AI systems across NLP, deep learning, and generative AI. Skilled in LLMs, RAG architectures, and prompt engineering, with strong expertise in Python, PyTorch, TensorFlow, and SQL. Experienced in building data pipelines, APIs, and distributed systems using Spark and Kafka. Strong MLOps background using Docker, Kubernetes, CI/CD, and MLflow to deliver production-grade solutions on AWS, Azure, and GCP.…AI/ML Engineer with 3+ years of experience designing and deploying scalable AI systems across NLP, deep learning, and generative AI. Skilled in LLMs, RAG architectures, and prompt engineering, with strong expertise in Python, PyTorch, TensorFlow, and SQL. Experienced in building data pipelines, APIs, and distributed systems using Spark and Kafka. Strong MLOps background using Docker, Kubernetes, CI/CD, and MLflow to deliver production-grade solutions on AWS, Azure, and GCP.

Niveda Vusse





AI/ML Engineer with 3+ years of experience designing and deploying scalable AI systems across NLP, deep learning, and generative AI. Skilled in LLMs, RAG architectures, and prompt engineering, with strong expertise in Python, PyTorch, TensorFlow, and SQL. Experienced in building data pipelines, APIs, and distributed systems using Spark and Kafka. Strong MLOps background using Docker, Kubernetes, CI/CD, and MLflow to deliver production-grade solutions on AWS, Azure, and GCP.…AI/ML Engineer with 3+ years of experience designing and deploying scalable AI systems across NLP, deep learning, and generative AI. Skilled in LLMs, RAG architectures, and prompt engineering, with strong expertise in Python, PyTorch, TensorFlow, and SQL. Experienced in building data pipelines, APIs, and distributed systems using Spark and Kafka. Strong MLOps background using Docker, Kubernetes, CI/CD, and MLflow to deliver production-grade solutions on AWS, Azure, and GCP.

Available to hire

AI/ML Engineer with 3+ years of experience designing and deploying scalable AI systems across NLP, deep learning, and generative AI. Skilled in LLMs, RAG architectures, and prompt engineering, with strong expertise in Python, PyTorch, TensorFlow, and SQL.

Experienced in building data pipelines, APIs, and distributed systems using Spark and Kafka. Strong MLOps background using Docker, Kubernetes, CI/CD, and MLflow to deliver production-grade solutions on AWS, Azure, and GCP.

Skills

AI Chatbot

Large Language Model

Prompt Engineering

Experience Level

AI Chatbot

Expert

Large Language Model

Expert

Prompt Engineering

Expert

Work Experience

AI/ML Engineer at Distyl AI

September 1, 2024 - Present

Designed end-to-end AI decisioning systems for healthcare prior authorization (PA) workflows using LLM-based inference to automate clinical guideline matching across 1,000+ payor policies for a Fortune 50 healthcare payor. Built LLM-powered agents with RAG, prompt engineering, and fine-tuning (LoRA, PEFT) to extract and reason over patient records and align clinical evidence with payor policies, improving accuracy by 25%. Developed multi-step agents to orchestrate retrieval, clinical reasoning, and decision routing across PA workflows with minimal human intervention. Reduced LLM inference latency by 40% using LangChain agent orchestration and LangSmith tracing; optimized FastAPI architecture and SQL query patterns to handle peak clinical data volumes without throughput degradation. Monitored production behavior via decision outcomes, escalation rates, and retrieval quality, iterating on prompts and tool configurations to improve approval accuracy over time.

AI/ML Engineer at Haptik

August 1, 2021 - July 1, 2023

Developed and deployed NLP-driven conversational AI chatbots using Python and TensorFlow for intent classification and entity recognition, enabling real-time support, lead capture, and workflow automation. Built and optimized dialogue management systems using RNN and LSTM architectures, improving intent recognition accuracy by 20% through hyperparameter tuning and iterative model refinement. Designed and integrated backend APIs using Flask and SQL; leveraged Snowflake for scalable storage and efficient management of large-scale conversational datasets. Implemented scalable data pipelines with Spark and Prefect for preprocessing and scheduling, improving pipeline execution efficiency by 25%. Evaluated models with precision, recall, and F1-score to ensure balanced classification performance and improved response relevance. Deployed ML solutions on Microsoft Azure with CI/CD pipelines, adding structured logging, monitoring, and BigQuery-based analytics for reporting and continuous improve