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

I am an AI Engineer passionate about turning complex data into actionable insights. I design and shipping AI-powered solutions that scale across large, unstructured datasets, leveraging LLMs, retrieval augmented generation (RAG), embeddings, and robust data pipelines. I enjoy collaborating with teams to solve real-world problems and continuously improve production-grade systems. In my work, I focus on building scalable backend architectures, asynchronous processing pipelines, and cloud deployments that deliver reliable and explainable AI outcomes for enterprise applications. I love turning messy data into structured, auditable workflows and delivering dashboards and tooling that empower non-technical stakeholders.…I am an AI Engineer passionate about turning complex data into actionable insights. I design and shipping AI-powered solutions that scale across large, unstructured datasets, leveraging LLMs, retrieval augmented generation (RAG), embeddings, and robust data pipelines. I enjoy collaborating with teams to solve real-world problems and continuously improve production-grade systems. In my work, I focus on building scalable backend architectures, asynchronous processing pipelines, and cloud deployments that deliver reliable and explainable AI outcomes for enterprise applications. I love turning messy data into structured, auditable workflows and delivering dashboards and tooling that empower non-technical stakeholders.

Punya Srivalli Nallamothu

AI Engineer, Data Scientist, Full Stack Developer, +2





I am an AI Engineer passionate about turning complex data into actionable insights. I design and shipping AI-powered solutions that scale across large, unstructured datasets, leveraging LLMs, retrieval augmented generation (RAG), embeddings, and robust data pipelines. I enjoy collaborating with teams to solve real-world problems and continuously improve production-grade systems. In my work, I focus on building scalable backend architectures, asynchronous processing pipelines, and cloud deployments that deliver reliable and explainable AI outcomes for enterprise applications. I love turning messy data into structured, auditable workflows and delivering dashboards and tooling that empower non-technical stakeholders.…I am an AI Engineer passionate about turning complex data into actionable insights. I design and shipping AI-powered solutions that scale across large, unstructured datasets, leveraging LLMs, retrieval augmented generation (RAG), embeddings, and robust data pipelines. I enjoy collaborating with teams to solve real-world problems and continuously improve production-grade systems. In my work, I focus on building scalable backend architectures, asynchronous processing pipelines, and cloud deployments that deliver reliable and explainable AI outcomes for enterprise applications. I love turning messy data into structured, auditable workflows and delivering dashboards and tooling that empower non-technical stakeholders.

Available to hire

I am an AI Engineer passionate about turning complex data into actionable insights. I design and shipping AI-powered solutions that scale across large, unstructured datasets, leveraging LLMs, retrieval augmented generation (RAG), embeddings, and robust data pipelines. I enjoy collaborating with teams to solve real-world problems and continuously improve production-grade systems.

In my work, I focus on building scalable backend architectures, asynchronous processing pipelines, and cloud deployments that deliver reliable and explainable AI outcomes for enterprise applications. I love turning messy data into structured, auditable workflows and delivering dashboards and tooling that empower non-technical stakeholders.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Intermediate

Language

English

Fluent

Work Experience

AI Engineer at World Link US

September 1, 2025 - Present

Designed and implemented an AI-driven compliance platform using LLMs and RAG pipelines to extract and normalize regulatory obligations into structured, queryable entities from 500+ page documents, enabling scalable, context-aware retrieval and significantly reducing manual compliance analysis effort. Architected a microservices-based backend (Node.js, TypeScript) by decomposing a monolithic application into independent services; built backend APIs for document ingestion, LLM orchestration, and analysis workflows, and developed React-based micro frontends with asynchronous pipelines and backend job processing for long-running document operations. Engineered hybrid retrieval pipelines (embedding + rule-based + LLM reasoning) to improve retrieval accuracy and reduce hallucinations in production AI workflows, enabling more reliable and explainable outputs for enterprise compliance use cases. Implemented a multi-tenant architecture with session and workspace management, supporting team-base

Student Assistant - Applied AI Engineer at University of Texas at Dallas

December 1, 2023 - May 1, 2024

Designed and deployed a Retrieval-Augmented Generation (RAG) model using LangChain, OpenAI embeddings, and Chroma to assist staff in guiding travelers through complex transit hubs; improved location-specific query relevance by 70%. Curated and processed a dataset of 150+ unstructured documents (PDFs, SOPs, FAQs) with metadata tagging and semantic chunking to enhance multi-turn retrieval and contextual accuracy. Developed a separate Digital Asset Management tool using Django, MySQL and Docker to organize multimedia course content; introduced dynamic filters by persona, location, and scenario, reducing asset retrieval time by 60%.

Software Engineer at Accenture

October 1, 2022 - June 1, 2023

Developed and customized a master data management solution using Java and TIBCO EBX for healthcare data of a pharmaceutical company, enabling insertions and cascading deletions of provider records across interconnected tables and ensuring data integrity and consistency across systems.