# Preetham Patlolla

> Applied AI Architect | Multi-Agent Systems & Edge Intelligence | Ex-NIST Researcher | Robotics M.S.

Location: Greater Hartford, United States
Profile: https://flows.cv/preethampatlolla

I am an AI Systems Architect who bridges the gap between deep research and production scale.

While many engineers focus solely on model training, I specialize in the "hard" problems of deployment: Orchestration, Constraints, and Physics. My background spans from theoretical research at NIST to shipping HIPAA-compliant Edge AI on 15W hardware, to architecting multi-agent systems handling 40M+ annual interactions.

Core Competencies:

Agentic Orchestration: Architected Federated Multi-Agent frameworks (Google ADK / Vertex AI) to unify fragmented enterprise chatbots, deflecting ~4M calls annually through dynamic intent routing.

Edge AI & Hardware: Specialized in deploying deep learning models on constrained devices (Intel NUC/Jetson). Expert in quantization, thermal management, and optimizing inference for non-RGB (IR/Depth) data.

Simulation & Digital Twins: Built graph-based simulation engines (DAGs) to model supply chain dynamics and generate synthetic training data for strategic decision-making.

Research: Deep background in Self-Supervised Learning, Latent Space Disentanglement, and Probabilistic Machine Learning (Variational Inference).

I don't just build models; I build the robust systems that allow them to survive in the real world.

## Work Experience
### Lead AI Engineer @ UnitedHealth Group (Optum) @ Virtusa
Jan 2024 – Present | Hartford, Connecticut, United States
•	Architected a Federated Multi-Agent System leveraging Google Agent Development Kit (ADK) to unify three fragmented Lines of Business (Rx, Benefits, Provider) into a single intelligent interface.
•	Designed a state-aware Orchestrator Agent that manages context across multi-turn conversations, dynamically routing intents to specialized sub-agents and solving the "siloed bot" problem.
•	Deployed a Retrieval-Augmented Generation (RAG) pipeline to automate Claims Inquiries (12% of total volume), projected to deflect ~4 million calls annually and save $8M in operational costs.
•	Led the first production deployment of CCAI Insights at scale, ingesting 35M+ annual calls into BigQuery for sentiment analysis, topic modeling, and advocate quality scoring.

### Sr. Machine Learning Engineer @ TADA
Jan 2023 – Jan 2024 | Peoria, Illinois, United States
•	Engineered a "Digital Twin" Simulation Engine based on Factory Physics to model complex supply chain dynamics.
•	Built a custom Directed Acyclic Graph (DAG) framework to propagate demand/supply constraints across network nodes, enabling stress-testing of inventory strategies before deployment.
•	Developed Graph Traversal Algorithms for Bill of Materials (BOM) explosion, optimizing inventory planning and identifying critical bottlenecks in real-time.
•	Generated massive-scale synthetic datasets via simulation to train "Supply Chain Copilot" models for strategic forecasting.

### Deep Learning Engineer @ VirtuSense
Jan 2022 – Jan 2023 | Peoria, Illinois, United States
•	Developed and deployed privacy-preserving fall detection models on constrained edge hardware (IntelNUC), utilizing exclusively IR/Depth data to maintain HIPAA compliance.
•	Diagnosed critical thermal throttling failures in field devices by analyzing CPU telemetry; identified third-party hardware defects and optimized inference pipelines to run stably on 15W power budgets.
•	Implemented Conv-LSTM architectures on temporal depth data to move from reactive fall detection to proactive intent prediction (predicting "exit-bed" motion 2 seconds in advance).
•	Optimized deep learning models using pruning and quantization (PyTorch), achieving real-time FPS on compute-constrained edge devices.

### Guest Researcher @ National Institute of Standards and Technology (NIST)
Jan 2020 – Jan 2021 | Gaithersburg, Maryland, United States
•	Conducted research on Self-Supervised Learning and Disentangled Representations for robotic pose estimation in unstructured environments.
•	Designed Denoising Autoencoders to extract pose-pertinent features from synthetic data, enabling robust performance in high-noise real-world settings without manual labels.
•	Benchmarked 3D-CNN vs. Conv-LSTM architectures for spatiotemporal modeling, establishing baselines for object manipulation tasks.


## Education
### Master's degree in Robotics
University of Maryland

### Bachelor's degree in Electrical and Electronics Engineering
Amrita Vishwa vidyapeetham, Bangalore


## Contact & Social
- LinkedIn: https://linkedin.com/in/preetham-patlolla

---
Source: https://flows.cv/preethampatlolla
JSON Resume: https://flows.cv/preethampatlolla/resume.json
Last updated: 2026-04-18