Shyam Sreenivasan

Feb 2026 – Present

Research Assistant

Northeastern University — Visual Intelligence Lab, Boston, MA | Advisor: Prof. Huaizu Jiang

• Researching domain generalization for 3D LiDAR semantic segmentation across heterogeneous environments (indoor, outdoor, aerial) using PyTorch and PointTransformerV3 as backbone
• Investigating domain normalization strategies to enable a single shared network to generalize across ScanNet, S3DIS, SemanticKITTI, and nuScenes without dataset-specific retraining
• Proposing a novel automatic domain normalization direction to adaptively infer domain boundaries — extending generalization beyond predefined environment categories
• Designing controlled experiments to quantify cross-domain performance degradation and dataset shift across heterogeneous point cloud distributions

Jul 2021 – May 2024

Lead Software Engineer

Giottus Technologies Pvt Ltd., Chennai, India

Distributed Systems · Real-Time Infrastructure · Engineering Leadership

Real-Time Systems & Connectivity

• Built WebSocket and gRPC-based real-time communication infrastructure for a live cryptocurrency trading platform, enabling low-latency persistent connections between clients, backend services, and third-party exchange APIs
• Implemented retry logic, message buffering, and fallback mechanisms for order processing pipelines over unreliable third-party connections — ensuring fault-tolerant, high-throughput transaction execution

Distributed Architecture & Scale

• Designed production-scale distributed microservices with Kafka, Docker, and Kubernetes handling 10× traffic spikes — achieving 300% throughput improvement, 70% faster deployments, and 45% downtime reduction
• Led monolith-to-microservices migration; pioneered Git Flow adoption and drove CI/CD practices across the engineering org

Security & Authentication

• Designed and built JWT-based authentication and RBAC authorization system from scratch using Spring Boot, including API key lifecycle management for third-party integrations (KYC providers, exchange APIs)
• Integrated confidence-scored KYC verification system with conservative approval thresholds and mandatory human review workflows for uncertain decisions — combining automated ML scoring with structured human oversight

Reliability, Testing & Observability

• Integrated Prometheus/Grafana and ELK Stack with automated alerting, achieving 99.9% uptime and 30% faster incident detection; diagnosed and resolved a race condition in live wallet updates via transaction replay and row-level locking
• Drove test-driven development culture — introduced scenario-based unit testing, parallel transaction simulation tests, QA/staging environments, and A/B rollout strategies

Product & Leadership

• Delivered end-to-end crypto platform features (KYC automation, Staking, SIP, Price Alerts, Crypto Baskets) driving 25% user adoption growth and 10% revenue increase
• Built internal CRM system from scratch for the operations team; mentored engineers on SOLID principles and design patterns, accelerating releases by 40% while reducing defects by 25%

Dec 2018 – Nov 2021

Machine Learning Engineer

CloudFabrix Software Pvt Ltd., Hyderabad, India

ML Pipelines · AIOps · Experimentation Platform

ML Platform & Tooling

• Built a core internal ML experimentation platform from scratch — evolving a plugin-based Python SDK into a full service supporting experiment tracking, model versioning, and reusable supervised/unsupervised pipelines adopted org-wide; reduced model-to-production time by 40%
• Collaborated with domain experts through human-in-the-loop validation workflows to diagnose model failure modes and refine behavior before production deployment

Pipelines & Anomaly Detection

• Designed real-time data ingestion pipelines with automated schema validation and quality checks over high-volume telemetry, reducing latency by 20% and enabling sub-second anomaly detection
• Applied unsupervised clustering (KMeans, DBSCAN, HDBSCAN) over large-scale infrastructure telemetry, achieving ~90% false-alert suppression while preserving critical failure signals

Forecasting & Monitoring

• Deployed Prophet and ARIMA-based time-series forecasting on rolling 90-day sensor windows, using forecast-residual bands to detect abnormal behavior — achieving 85% prediction accuracy and reducing unplanned downtime by 30%
• Designed data storage schemas and partitioning strategies for large-scale time-series and event data to support analytics and ML workflows

Nov 2017 – Dec 2018

Software Developer

Geazy Technologies LLP, Chennai, India

• Re-engineered core ad posting platform components, improving performance by 15% and reducing operational costs by 10%
• Built efficient data transformation parsers in PHP for large-scale data processing pipelines
• Resolved production issues in chatbot integrations, reducing downtime by 40%