01
AI/ML Evaluation & Quality
Evaluate AI-generated code, technical reasoning, data-analysis solutions, and model outputs for correctness, consistency, evidence, and real-world usefulness.
Available for remote opportunities
Senior Software Engineer specializing in AI/ML evaluation, data engineering, backend platforms, APIs, automation, and cloud-ready systems.
I turn ambiguous technical problems into reliable products, clean data workflows, and maintainable production systems.
6+
Years of experience
3
Core specialties
Remote
United States
What I do
A practical blend of software engineering, data systems, and AI quality work—focused on reliability, clear architecture, and measurable usefulness.
01
Evaluate AI-generated code, technical reasoning, data-analysis solutions, and model outputs for correctness, consistency, evidence, and real-world usefulness.
02
Build repeatable ingestion, validation, transformation, and reporting workflows that turn raw operational data into trusted datasets and actionable analysis.
03
Design production services, REST and GraphQL APIs, third-party integrations, webhooks, and resilient data-access layers for customer-facing and internal products.
04
Improve delivery and production confidence through CI/CD, containerization, infrastructure automation, testing, structured logging, metrics, tracing, and incident-focused debugging.
Selected work
A structured approach for evaluating code, technical reasoning, evidence, edge cases, and recurring model failure patterns.
Validated and normalized third-party data, added resilient error handling, and exposed reliable services to application and reporting layers.
Python and SQL workflows for ingestion, cleaning, deduplication, validation, transformation, dashboards, and operational reporting.
About & experience
I’m a senior software engineer with more than six years of experience across backend development, full-stack delivery, data automation, analytics, and AI/ML evaluation.
I’m strongest in environments where the problem is partially defined, the data is messy, or reliability matters more than a flashy demo.
Independent Contractor · Remote
Evaluate AI-generated code, data-analysis solutions, machine-learning reasoning, API designs, debugging approaches, and technical explanations. Produce precise, evidence-based feedback on reasoning gaps, hallucinations, missing edge cases, and data-quality concerns.
Seven Hills Technology · Remote
Designed and maintained production backend services, API integrations, data-ingestion workflows, and full-stack features using Python, Node.js, TypeScript, React, PostgreSQL, MongoDB, AWS, and Docker.
IntelliX Software Inc · Remote
Built Python and SQL data workflows, reporting automation, dashboards, and internal tools that transformed spreadsheets, APIs, and database records into dependable datasets and practical analytical findings.
How I work
01
Clarify users, data ownership, failure modes, security needs, and operational limits before choosing architecture or tools.
02
Treat logging, metrics, tracing, testing, and recoverability as part of the system—not cleanup work after launch.
03
Leave behind maintainable code, explicit tradeoffs, clear interfaces, and documentation that helps the next engineer move faster.
Engineering notes
AI quality · 9 min read
A practical framework for rubrics, evidence, failure categories, edge cases, and repeatable human review.
Backend · Coming soon
Timeouts, retries, idempotency, contract validation, observability, and graceful degradation.
Data · Coming soon
Validation, lineage, schema drift, deduplication, backfills, monitoring, and trustworthy downstream outputs.
Let’s connect
I’m available for fully remote software engineering opportunities and select contract projects involving AI/ML evaluation, backend systems, data engineering, API integrations, and automation.