Projects

Backend and AI platform engineering — infrastructure and production AI case studies.

Tech filter

4 project(s) matched.

Lydia Agentic AI Assistant and Event Delivery Platform

Software Engineer · 2025

Built Lydia, an agentic AI assistant for high-volume telemetry analytics, and designed the durable event-delivery platform behind its multi-turn tool-calling workflows.

Delivery control path

Receive100%
Outbox92%
Deliver88%
Replay95%
TypeScriptMySQLClickHouseKafka/MSKRedis StreamsSocket.ioDuckDBEC2OpenTelemetry
Read more →
Tool-calling SQL · ClickHouse · Outbox + MSK

Behavioral Efficiency Scoring with Double Machine Learning

Software Engineer · Dec 2024 - Present

Built a causal evaluation framework that separated behavioral signal from environmental confounders, producing fair rankings and actionable coaching insights for operations teams.

PythonPyTorchScikit-LearnSHAPAWS S3Statistical Inference
Read more →
Team-wide · Confounder-adjusted · Significant, recurring

Event-Driven Telemetry Fan-Out for Real-Time Operations

Software Engineer · Dec 2024 - Present

Built Kafka and Redis Pub/Sub fan-out paths for live high-volume telemetry, enabling sub-second operator dashboard updates and horizontally scalable real-time processing.

Telemetry fan-out path

Ingest100%
Fan out84%
Serve82%
Tune72%
TypeScriptNestJSRedisKafkaAWS ECSMySQLMQTT
Read more →
High-volume · Sub-second · Substantial

Self-Hosted LLM Inference for Lydia

Software Engineer · 2024 - 2025

Deployed vLLM and llama.cpp on on-prem GPU infrastructure behind EC2, NGINX, and Route 53, replacing hosted inference and reducing the assistant's serving cost.

Adoption milestones

Engineers
Queries/day
Cost saved
vLLMllama.cppNGINXRoute 53EC2PythonTypeScript
Read more →
Internal eng team · Regular usage · Meaningful