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

I'm an AI/ML engineer with 4+ years of experience building production-grade ML systems across financial services and healthcare. I specialize in deep learning, LLM optimization, and real-time data infrastructure to reduce costs and boost model performance. I translate complex business requirements into end-to-end ML pipelines—from raw data ingestion to model serving—using cloud-native and microservices architectures on AWS. I collaborate with cross-functional teams to deliver scalable, reliable solutions that drive measurable outcomes.…I'm an AI/ML engineer with 4+ years of experience building production-grade ML systems across financial services and healthcare. I specialize in deep learning, LLM optimization, and real-time data infrastructure to reduce costs and boost model performance. I translate complex business requirements into end-to-end ML pipelines—from raw data ingestion to model serving—using cloud-native and microservices architectures on AWS. I collaborate with cross-functional teams to deliver scalable, reliable solutions that drive measurable outcomes.

Uday Charan Reddy Pati

Data Scientist, AI Engineer, Data Analyst, +2





I'm an AI/ML engineer with 4+ years of experience building production-grade ML systems across financial services and healthcare. I specialize in deep learning, LLM optimization, and real-time data infrastructure to reduce costs and boost model performance. I translate complex business requirements into end-to-end ML pipelines—from raw data ingestion to model serving—using cloud-native and microservices architectures on AWS. I collaborate with cross-functional teams to deliver scalable, reliable solutions that drive measurable outcomes.…I'm an AI/ML engineer with 4+ years of experience building production-grade ML systems across financial services and healthcare. I specialize in deep learning, LLM optimization, and real-time data infrastructure to reduce costs and boost model performance. I translate complex business requirements into end-to-end ML pipelines—from raw data ingestion to model serving—using cloud-native and microservices architectures on AWS. I collaborate with cross-functional teams to deliver scalable, reliable solutions that drive measurable outcomes.

Available to hire

I’m an AI/ML engineer with 4+ years of experience building production-grade ML systems across financial services and healthcare. I specialize in deep learning, LLM optimization, and real-time data infrastructure to reduce costs and boost model performance.

I translate complex business requirements into end-to-end ML pipelines—from raw data ingestion to model serving—using cloud-native and microservices architectures on AWS. I collaborate with cross-functional teams to deliver scalable, reliable solutions that drive measurable outcomes.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Work Experience

AI/ML Engineer at JPMorgan Chase

August 1, 2024 - Present

Built a real-time fraud detection system using multimodal deep learning, fusing transaction sequences, document text, and behavioral patterns, achieving 98.4% classification accuracy with sub-150ms latency on 8,000+ daily requests. Reduced AWS inference costs by 31% through structured pruning and INT8 quantization while preserving F1 within 0.5% of baseline across 3 production environments. Implemented a compliance document intelligence layer using RAG pipelines over regulatory filings and internal policy corpora, reducing analyst review time by 35% and increasing reporting accuracy by 22% across 6 compliance workflows. Designed a reinforcement learning-based case prioritization engine with real-time signals and investigator feedback loops, cutting mean time-to-resolution by 18% and increasing daily case closures by 15%. Engineered a vector retrieval system indexing 15M+ records using FAISS and pgvector enabling sub-800ms similarity search for fraud pattern matching. Established an MLO

Machine Learning Scientist at HCL Technologies

January 1, 2021 - July 31, 2023

Led development of a clinical recommendation platform processing 20+ TB/month of EHR and claims data across 12+ hospital systems, delivering near real-time decision support with 99.9% pipeline availability. Built ensemble readmission and ICU demand forecasting models (XGBoost, LightGBM, LSTM) with 30+ engineered clinical features, reducing avoidable 30-day readmissions by 20% and improving care planning accuracy by 15%. Developed a causal inference framework using propensity score matching and CUPED to evaluate intervention impact across cohorts on 2M+ patient records. Built GNN-based care pathway recommendations improving relevance scores by 17% and reducing hospital resource waste by 12% across 5 departments. Implemented streaming data ingestion with Apache Kafka and Spark Structured Streaming to merge EHR, lab, claims, and ADT feeds with <90-second feature freshness for real-time risk scoring. Delivered executive analytics dashboards in Power BI on top of cloud data platforms, infor