Available for opportunities

Srinivas
Gampasani

|

Generative AI Engineer with 3+ years building production-grade LLM systems, RAG pipelines, and scalable ML infrastructure across healthcare and enterprise domains. Specialized in turning complex AI research into real-world impact.

40%Accuracy boost
50K+Docs processed
3+Years experience
View My Work Contact Me
Srinivas Gampasani
LLM
RAG
MLOps
Python
Scroll
What I Know

Technical Skills

End-to-end expertise from data ingestion to production deployment

Generative AI & LLMs

LangChainLlamaIndexRAGFine-Tuning LoRA / QLoRAPrompt EngineeringFAISS OpenAI APIAzure OpenAIAI Agents

Machine Learning & Deep Learning

PyTorchTensorFlowScikit-learn XGBoostLightGBMTransformers CNNsBERT / GPTSHAP / LIME

Programming & NLP

PythonSQLPySparkJava TypeScriptBashNER Sentence TransformersOCR

Data Engineering & Big Data

Apache SparkKafkaAirflow dbtSnowflakeBigQuery Delta LakeHadoopETL Pipelines

MLOps & Deployment

MLflowDockerKubernetes CI/CDFastAPIFlask PrometheusGrafanaJenkins

Cloud & Databases

AWS SageMakerAzure MLGCP Vertex AI PineconeWeaviateMilvus PostgreSQLRedisNeo4j
What I've Built

Featured Projects

Production-grade AI/ML systems solving real business problems

Details
Generative AI

Enterprise AI Knowledge Retrieval (RAG)

Production-grade RAG system enabling real-time Q&A across 100K+ enterprise documents. Achieved sub-second latency with 35% improvement in response accuracy.

LangChainFAISSAzure OpenAIFastAPIDocker
35% accuracy boost
Sub-second latency
Details
NLP

Clinical NLP Document Intelligence

HIPAA-compliant NLP pipeline for clinical text summarization and structured information extraction from 50K+ patient records, reducing manual effort by 30%.

BERTTransformersspaCyApache SparkPython
30% time saved
50K+ docs
Details
Generative AI

Multi-Agent AI Orchestration Framework

LangGraph-powered multi-agent system enabling complex task decomposition, autonomous tool use, and collaborative reasoning across specialized AI agents.

LangGraphLangChainGPT-4FastAPIRedis
5+ agents
Autonomous tasks
Details
Generative AI

LLM Fine-Tuning Pipeline (LoRA / QLoRA)

End-to-end fine-tuning pipeline for domain adaptation of open-source LLMs using PEFT techniques, reducing compute cost by 60% while maintaining model quality.

LoRAQLoRAPEFTPyTorchHuggingFace
60% cost reduction
Domain-specific
Details
Machine Learning

Demand Forecasting ML System

Scalable demand forecasting engine using XGBoost and Neural Networks for Colgate-Palmolive, achieving 20% prediction accuracy improvement with automated retraining.

XGBoostTensorFlowAirflowMLflowPySpark
20% accuracy gain
Auto-retrain
Details
Machine Learning

Real-Time Anomaly Detection System

Streaming anomaly detection pipeline using Kafka and Isolation Forest for real-time monitoring of enterprise data streams, flagging outliers with 95%+ precision.

KafkaIsolation ForestScikit-learnFastAPIDocker
Real-time detection
95%+ precision
View All 13 Projects — Full Case Studies
My Journey

Work Experience

Building AI solutions that scale from prototype to production

Generative AI Engineer & Data Scientist

Ascension Via Christi Health  |  Wichita, KS
Sep 2024 – Present
  • Architected production-grade RAG pipelines using LLMs, improving answer relevance by 40% and enabling real-time AI decision support across clinical workflows.
  • Engineered scalable ETL and embedding pipelines processing 50,000+ clinical documents using Python, Apache Spark, and FAISS.
  • Designed NLP pipelines for clinical text summarization and information extraction, reducing manual effort by 30%.
  • Implemented end-to-end MLOps pipelines with MLflow, reducing deployment errors by 30% and enabling zero-downtime releases.
  • Integrated OpenAI and Azure OpenAI APIs into enterprise clinical applications ensuring HIPAA compliance.
LangChainAzure OpenAIFAISSMLflowKubernetesApache Spark

Machine Learning Engineer & Data Engineer

Colgate-Palmolive  |  Topeka, KS
Dec 2023 – Aug 2024
  • Built predictive analytics and demand forecasting models improving prediction accuracy by 20% using XGBoost, Random Forest, and Neural Networks.
  • Optimized SQL queries and Apache Spark pipelines, reducing data processing time by 25%.
  • Deployed ML models as REST APIs using FastAPI and Docker, enabling low-latency real-time inference.
  • Automated model retraining workflows, cutting deployment time by 20%.
XGBoostTensorFlowKafkaFastAPIAirflowDocker

Machine Learning Engineer

Maxton Technology Pvt. Ltd.  |  Bangalore, India
Aug 2022 – Aug 2023
  • Developed ML models for demand forecasting, anomaly detection, and predictive analytics, improving accuracy by 15%.
  • Built scalable ETL pipelines reducing pipeline latency by 25% using Python and distributed systems.
  • Designed data pipelines on GCP for large-scale processing and downstream analytics.
  • Deployed models via Flask, Docker, and RESTful APIs enabling real-time production inference.
PythonGCPFlaskDockerScikit-learn

M.S. in Artificial Intelligence

Saint Louis University  |  St. Louis, MO, USA
Aug 2023 – Dec 2025
AWS Certified Data Analytics Future Skills Prime — AI Future Skills Prime — Data Science Future Skills Prime — NLP Coursera — Machine Learning
Let's Connect

Get In Touch

Open to roles in AI Engineering, ML Engineering, and Data Science

Let's build something great

I'm actively looking for opportunities in Generative AI, Machine Learning, and Data Engineering. Whether you have a project, a role, or just want to talk AI — I'd love to hear from you.

Email
srinivasgampasani7@gmail.com
LinkedIn
srinivas-gampasani
GitHub
srinivas-gampasani
Phone
+1 314-548-3799

I typically respond within 24 hours.