Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I’m a Senior Software Engineer in Test with 5+ years of experience across platforms and AI-driven products. I lead test strategy from scratch, defining risks and shipping with confidence. I own quality E2E across classic UI, APIs, and AI systems. I design test plans for AI chat and conversational workflows, test intent detection, tool execution, retries and final system state. I build automated E2E tests for AI workflows, use LLM judges with clear rubrics to score accuracy, tone, safety and instruction adherence, and I lead swarm test planning to align AI engineers, PMs and designers on quality before release.…I’m a Senior Software Engineer in Test with 5+ years of experience across platforms and AI-driven products. I lead test strategy from scratch, defining risks and shipping with confidence. I own quality E2E across classic UI, APIs, and AI systems. I design test plans for AI chat and conversational workflows, test intent detection, tool execution, retries and final system state. I build automated E2E tests for AI workflows, use LLM judges with clear rubrics to score accuracy, tone, safety and instruction adherence, and I lead swarm test planning to align AI engineers, PMs and designers on quality before release.

Artur Bikulov

AI Engineer, AI Developer, Data Scientist, +2





I’m a Senior Software Engineer in Test with 5+ years of experience across platforms and AI-driven products. I lead test strategy from scratch, defining risks and shipping with confidence. I own quality E2E across classic UI, APIs, and AI systems. I design test plans for AI chat and conversational workflows, test intent detection, tool execution, retries and final system state. I build automated E2E tests for AI workflows, use LLM judges with clear rubrics to score accuracy, tone, safety and instruction adherence, and I lead swarm test planning to align AI engineers, PMs and designers on quality before release.…I’m a Senior Software Engineer in Test with 5+ years of experience across platforms and AI-driven products. I lead test strategy from scratch, defining risks and shipping with confidence. I own quality E2E across classic UI, APIs, and AI systems. I design test plans for AI chat and conversational workflows, test intent detection, tool execution, retries and final system state. I build automated E2E tests for AI workflows, use LLM judges with clear rubrics to score accuracy, tone, safety and instruction adherence, and I lead swarm test planning to align AI engineers, PMs and designers on quality before release.

Available to hire

I’m a Senior Software Engineer in Test with 5+ years of experience across platforms and AI-driven products. I lead test strategy from scratch, defining risks and shipping with confidence. I own quality E2E across classic UI, APIs, and AI systems.
I design test plans for AI chat and conversational workflows, test intent detection, tool execution, retries and final system state. I build automated E2E tests for AI workflows, use LLM judges with clear rubrics to score accuracy, tone, safety and instruction adherence, and I lead swarm test planning to align AI engineers, PMs and designers on quality before release.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Language

English

Fluent

Russian

Fluent

Uzbek

Fluent

Spanish; Castilian

Intermediate

Work Experience

Senior Software Development Engineer Test - AI Systems at Calendly

October 1, 2025 - Present

Led quality for an AI-powered scheduling assistant chat. Defined AI chat behavior, tool execution and state changes, and end-user outcomes; created comprehensive AI test plans and executable tests; built LLM judge-based evaluations to score responses on correctness, tone, safety and instruction adherence; developed modular automation frameworks and regression pipelines; conducted swarm test planning with AI engineers, PMs and designers; validated Firebase-backed conversation state, idempotency, and safety boundaries across SMS and voice flows.

AI Task Developer (Part-time Contractor) at Snorkel AI

September 1, 2025 - Present

Developed advanced coding and reasoning tasks to train and evaluate LLMs. Wrote instructions, implemented solutions and built automated tests in Docker environments using JavaScript, TypeScript and Python.

Senior Software Engineer in Test at LevelTen Energy

May 1, 2025 - January 1, 2026

Led testing strategy for the core energy marketplace platform, building scalable test automation using Cypress and TypeScript for dozens of feature teams. Designed and maintained reusable test components, authored detailed test plans, led Swarm Test Planning sessions, and established CI pipelines for UI and API regression. Achieved 80%+ unit test coverage across new modules and collaborated with multiple tooling ecosystems.

Software Engineer In Test at LevelTen Energy

October 1, 2022 - July 1, 2025

Developed E2E test automation using Cypress with JavaScript to improve coverage across frontend, backend and API layers. Implemented multi-browser component testing, tagged tests for CI filtering, and integrated pipelines to run tests on PRs and deployments. Led Swarm Test Planning sessions and defined overarching test strategy.

QA Engineer II at Amazon

May 1, 2022 - September 1, 2022

QA engineer responsible for building test planning for a new web-based console for Amazon's distribution centers. Performed functionality, validation, end-to-end user and regression testing; prioritized bugs, measured code coverage, wrote SQL queries for data validation, used Charles Proxy, and maintained test artifacts in JIRA in an Agile environment.

QA Engineer at Flatlay Inc.

August 1, 2018 - May 1, 2022

Ticket testing, test case creation, bug reporting and verification. Wrote, ran and maintained automation tests; collaborated with developers to validate user stories; maintained Cypress automation framework; performed regression testing; used SQL for test data and bug trend analysis.