Hello!
I'm Sakshi Patel, an AI Engineer with a strong background in building production-grade generative AI and multi-agent systems, driving measurable business impact.
Get in touch sakshipatel2598@gmail.com
Recent graduate with a Master's in Information Technology and Management from The University of Texas at Dallas. I am an AI Engineer with a strong background in building production-grade generative AI and multi-agent systems, seeking to accelerate AI-driven solutions and drive measurable business impact.
Currently, I work as an AI Engineer at Worldlink, where I led the design and deployment of an AI-enabled supply-chain decision platform that cut manual analysis cycles by 40% and improved route-planning efficiency by 25%.
Previously, I worked as a GenAI Engineer Intern at Insight Global, delivering a GenAI SOW generator that reduced drafting effort by 30% and implementing RAG pipelines that boosted document accuracy by 25%. Before that, I gained strong industry experience at LTIMindtree, engineering enterprise-scale financial integration systems processing 100M+ transactions with 99.99% uptime.
Drafting a Statement of Work (SOW) is a vital part of business and legal projects. It outlines key details like deliverables, timelines, responsibilities, and legal terms. However, creating these documents is often a slow and complex process. This paper introduces a new AI-driven automation system that makes the entire SOW drafting process faster, easier, and more accurate. Instead of relying completely on humans, the system uses three intelligent components or 'agents' that each handle a part of the job.
This solution shows how artificial intelligence can be used to support legal and business professionals by taking care of routine work and helping them focus on more important decisions. It's a step toward making legal processes smarter, faster, and more reliable.
Read more...
- Python
- JavaScript
- Typescript
- SQL
- Java
- R
- React.js
- Node.js
- Flask
- GraphQL
- Tableau
- Power BI
- MongoDB
- PostgreSQL
- Snowflake
- Neo4j
- AWS
- Azure
- Docker
- LangGraph & LangChain
- RAG
- Multi-Agent Orchestration
- Prompt and Context Engineering
- Vector Search
- LLM Evaluation (LLM-as-Judge)
- Databricks (Generative AI Engineer – Associate)
- Databricks (Data Engineer – Associate)
- SnowPro® Core Certification
- Designed and shipped production-grade AI-enabled tools and agentic workflows using LangGraph, transforming supply-chain consulting processes into AI-driven decision systems adopted by internal teams.
- Improved complex consulting workflows (routing, tariff computation, risk modeling) into modular AI services, reducing manual analysis cycles by 40% and accelerating decision turnaround.
- Architected stateful multi-agent systems with token budgeting, structured reasoning, and SQL-backed session persistence, and added LLM-as-judge evaluation to benchmark outputs; this ensured reliable LLM deployments and accelerated model-optimization cycles
- Built AI-powered route optimization services using Neo4j graph algorithms (Dijkstra, k-shortest path), improving route-planning efficiency by 25% and enabling real-time decision support.
- Engineered modular, reusable agent architectures with configurable prompts, tools, and memory layers, enabling rapid adaptation across multiple consulting workflows without rebuilding core orchestration logic.
- Built a production-ready AI-powered SOW Generator using LangGraph and multi-agent orchestration, automating drafting, validation, and structured feedback loops - reducing manual drafting effort by 30%.
- Designed Retrieval-Augmented Generation (RAG) architecture with PostgreSQL (pgvector) embeddings, improving enterprise document accuracy by 25%.
- Deployed GenAI services on Azure using Azure OpenAI and scalable compute infrastructure, ensuring secure and performant production usage.
- Containerized and deployed GenAI services as production-ready APIs using Docker and Azure infrastructure, enabling scalable enterprise adoption and secure integration into existing consulting workflows
- Mentored 50+ students on AWS, Hadoop/Spark, Tableau, Power BI, and Python for real-world data analytics projects.
- Developed curriculum and provided feedback to enhance analytical skills
- Engineered enterprise-scale financial integration systems processing 100M+ transactions with 99.99% uptime, supporting large-scale payment system migration.
- Designed automated validation and ingestion pipelines reducing manual intervention by 50% and improving deployment reliability across SIT and UAT environments.
- Authored high-level and low-level design documents for systems built with TypeScript and Python, outlining trade-offs, integration patterns, and data flows; this clarified stakeholder expectations and sped up design approvals
- Led issue resolution in high-ambiguity, multi-system environments, ensuring stable production deployments across distributed systems.
- Created Power BI and Tableau dashboards highlighting user retention and growth, increasing consultation-based revenue by 25%.
- Developed SQL queries and AWS Athena pipelines for real-time metrics and program performance analysis.
- Automated Excel-based stakeholder reports, reducing repetitive tasks by 50%
- Built and optimized SQL pipelines to extract and transform REST API data for business reporting, decreasing query response time by 40%.
- Designed and deployed Tableau dashboards for automated insights, reducing manual reporting by 20%.
Integrated an internal knowledge management chatbot using LangGraph and OpenAI, enabling employees to retrieve insights from 1,000+ documents with 85% retrieval accuracy.
Engineered an end-to-end clinical analytics pipeline processing millions of structured and time-series ICU records using Python and SQL to support predictive modeling. Built and evaluated ML models (Logistic Regression, Random Forest, XGBoost) to predict mortality risk and ICU length of stay, achieving measurable AUC and F1-score improvements.
Built Hadoop/Spark infrastructure to process 10M+ records, reducing latency by 30%. And created React-based dashboard integrated with Tableau to track driver behavior and incident risk zones, reducing fleet accidents by 25%.
Analyzed 3M+ grocery transactions with Python & SQL, improving cross-sell strategy by 15% & forecast accuracy by 25%. And Visualized key insights using Tableau dashboards to support strategic planning and boost retention by 18%.