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

I am Shweta Gupta, an AI Engineer specializing in LLMs, RAG, prompt engineering, GenAI safety, NLP pipelines, autonomous agents, and MLOps. I design retrieval architectures, embeddings, vector databases, and cloud deployments to deliver production LLM applications across finance, enterprise, and SaaS domains. I enjoy turning data into actionable AI solutions, leading end-to-end delivery, and mentoring teammates. I am passionate about building grounded, safe AI systems and driving measurable business impact.…I am Shweta Gupta, an AI Engineer specializing in LLMs, RAG, prompt engineering, GenAI safety, NLP pipelines, autonomous agents, and MLOps. I design retrieval architectures, embeddings, vector databases, and cloud deployments to deliver production LLM applications across finance, enterprise, and SaaS domains. I enjoy turning data into actionable AI solutions, leading end-to-end delivery, and mentoring teammates. I am passionate about building grounded, safe AI systems and driving measurable business impact.

Shweta Gupta

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





I am Shweta Gupta, an AI Engineer specializing in LLMs, RAG, prompt engineering, GenAI safety, NLP pipelines, autonomous agents, and MLOps. I design retrieval architectures, embeddings, vector databases, and cloud deployments to deliver production LLM applications across finance, enterprise, and SaaS domains. I enjoy turning data into actionable AI solutions, leading end-to-end delivery, and mentoring teammates. I am passionate about building grounded, safe AI systems and driving measurable business impact.…I am Shweta Gupta, an AI Engineer specializing in LLMs, RAG, prompt engineering, GenAI safety, NLP pipelines, autonomous agents, and MLOps. I design retrieval architectures, embeddings, vector databases, and cloud deployments to deliver production LLM applications across finance, enterprise, and SaaS domains. I enjoy turning data into actionable AI solutions, leading end-to-end delivery, and mentoring teammates. I am passionate about building grounded, safe AI systems and driving measurable business impact.

Available to hire

I am Shweta Gupta, an AI Engineer specializing in LLMs, RAG, prompt engineering, GenAI safety, NLP pipelines, autonomous agents, and MLOps. I design retrieval architectures, embeddings, vector databases, and cloud deployments to deliver production LLM applications across finance, enterprise, and SaaS domains.

I enjoy turning data into actionable AI solutions, leading end-to-end delivery, and mentoring teammates. I am passionate about building grounded, safe AI systems and driving measurable business impact.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Language

English

Fluent

Work Experience

AI Engineer at APPLIED MEDICAL

August 1, 2025 - September 5, 2025

Built customer segmentation models using K-means clustering and causal inference on SAP S/4HANA data, increasing customer retention by 15%. Developed analytics pipelines merging CRM and transactional data to support evidence-based decisions and improved customer journey analysis. Automated order acknowledgment workflows, saving 1.6 FTE and improving accuracy/time-to-delivery.

AI Engineer at INGRAM MICRO

May 1, 2025 - September 5, 2025

Raised internal product catalog accuracy by 25% via a custom scraping and LLM enrichment pipeline; scraped product pages using model numbers and applied Gemini 1.5 Pro with structured prompts to auto-generate metadata, reducing manual effort by 40+ hours/month. Developed and fine-tuned classification models (Logistic Regression, XGBoost, LLM) to classify 10K+ SKUs, improving labeling accuracy by 22%. Designed prototype pipelines to move data to/from LLMs for training and evaluation; applied Gemini-based orchestration to boost metadata accuracy by 30%.

Senior Software Engineer at ACCENTURE

July 1, 2024 - September 5, 2025

Increased reconciliation precision from 65% to 95% using SQL-based validation; implemented automated monitoring scripts for anomaly detection in production pipelines. Built and scaled 4+ real-time ETL pipelines on AWS, reducing data latency by 40% and handling multi-terabyte datasets. Applied predictive modeling and time-series forecasting to improve KPI predictions. Led a team of 3 junior analysts and advanced analytics adoption; implemented CI/CD-enabled ETL pipelines.

Software Engineer at ORACLE FINANCIAL SERVICES SOFTWARE

August 1, 2022 - September 5, 2025

Supported real-time ML model integration by building scalable microservices and data pipelines for financial transactions, enabling continuous feature delivery with 99.9% uptime across 10+ services. Modernized a legacy monolith to Java (Spring Boot) REST microservices; introduced Kafka-based, event-driven integrations and idempotent APIs, reducing downtime by 30%.

AI Engineer at EASYBEE AI

November 1, 2025 - Present

Designed a RAG-based knowledge base and retrieval safety workflows, structuring policies, pricing rules, and FAQs into retrievable documents to enable policy-aligned responses and reduce hallucinations in live conversations.

Senior Software Engineer at ACCENTURE

September 1, 2022 - July 1, 2024

Implemented intent classification, entity extraction, and semantic search; tuned models with LoRA/prompts for domain vocabulary and compliance; built Elasticsearch-based grounding; productionized services with FastAPI and Java; created telemetry pipelines and A/B testing for uplift and cost; established model evaluation & monitoring and risk controls.

Software Engineer at ORACLE

August 1, 2018 - August 1, 2022

Built scalable microservices and data pipelines for real-time ML feature delivery; modernized a legacy monolith into Java/Spring Boot REST microservices; introduced Kafka-based, event-driven integrations and idempotent APIs, improving resiliency and cutting downtime by 30%.