Case studies

Work

Case studies from real roles across aviation, finance, and energy, plus two personal AI projects. Not screenshots — each one walks through the actual engineering: the problem, the options I weighed, the call I made, the failure I hit, and the measured outcome.

Every study is built to be scanned in fifteen seconds or read in full. If you want proof of how I work, this is the page to start on.

bet2025 – Present

Internal AI Agents for Backend Operations — Gated by Evals

Built internal AI agents that automate log analysis, anomaly detection, data validation, and incident summarization — with eval suites that catch regressions before every release.

PythonLLM APIsTool CallingRAGEmbeddingsLLM Evals

Release gating

evals every release
spot checks
→
architectureJun 2025 – Present

Owning Solar Billing & Time-of-Use Rate Optimization End to End

Own solar billing and time-of-use rate optimization end to end — API design, data modelling, release — turning seasonal and mid-cycle rate logic into accurate, repeatable costs.

JavaPythonREST APIsCassandraAWSRedshift

Ownership

end to end
→
alignmentNov 2024 – May 2025

A Talent-Pool Tracking App, From Scratch to Production in Two Months

Took a talent-pool tracking app from scratch to production in 2 months — React SPA over a Node.js REST API, secured with Azure AD — by turning stakeholder needs into UI flows and API contracts.

TypeScriptReactNode.jsREST APIsSQLAzure AD

Time to production

2 months
from scratch
→
architectureJun 2025 – Present

Event-Driven Services for High-Volume Energy & EV Data

Designed and scaled event-driven services on AWS EventBridge and SQS with idempotent consumers and retries, and led the Cassandra migration from Astyanax to the DataStax driver.

JavaPythonAWS EventBridgeSQSLambdaKafka

Cassandra client library

DataStax
Astyanax
→
architectureOct 2023 – Sep 2024

Integrating 3 GDS Platforms and 35+ Airline APIs

Integrated 3 GDS systems via SOAP (+13% revenue) and built and optimized 35+ REST, GraphQL, and SOAP airline APIs with validation and structured errors (+8% backend performance).

Node.jsSOAPRESTGraphQLPythonDocker

Revenue

+13%
baseline
→
architectureOct 2023 – Sep 2024

Migrating Legacy SQL Databases to MongoDB for Airline Integrations

Led the migration of legacy SQL databases to MongoDB — schemas redesigned around access patterns, reporting moved onto aggregation pipelines — for 20% faster queries.

Node.jsMongoDBMySQLAggregation PipelinesGCP

Query performance

20% faster
baseline
→
architectureSep 2024 – Oct 2024

Replacing Legacy Logins with Azure AD Across Multiple Applications

Integrated Azure Active Directory authentication across multiple applications at Indigo, retiring the legacy logins and improving login performance by 25%.

Azure ADOAuth2OIDCJWTREST APIsMicroservices

Login performance

+25%
baseline
→
betPersonal project

AgentOps — A Multi-Agent Incident-Response System

A LangGraph multi-agent system (planner, log analyst, fixer) that takes an incident from alert to root cause to a draft fix — with MCP tools, an eval harness, and human approval on every change.

PythonLangGraphMCPFastAPIDockerOpenTelemetry

Eval dimensions per run

4
→
architecturePersonal project

DocuMind — A Production RAG Platform

A multi-tenant RAG platform with streamed, cited answers — hybrid BM25 + embedding retrieval with reranking, a Redis semantic cache, and RAGAS scoring on every change.

TypeScriptNext.jsPostgreSQLpgvectorRedisRAGAS

Retrieval

hybrid + rerank
vector-only
→