AI Engineering Lead (Agentic Development)
# AI Engineering Lead (Agentic Development) **Niuro** · Remote · `Remote` 🕒 **Статус:** *Опубликовано: сегодня* · *Источник: Get on Board (LATAM)* --- ### About the Role - Lead-level experience, with at least 5 years in software engineering and technical leadership of concurrent development workstreams. - Hands-on experience with several AI coding tools or agent frameworks. - Strong ability to understand code changes, investigate defects, run meaningful tests, and evaluate AI-generated output. - Experience using command-line tools, shell scripting, Git, and repeatable software development workflows. - Experience building and troubleshooting automation for concurrent sessions or development processes. - Experience with macOS automation, or equivalent desktop automation experience with the ability to learn macOS-based workflows. - Ability to organize parallel workstreams, identify dependencies, assign clear ownership, and prevent duplicated work. - Ability to write precise task instructions, concise progress summaries, evidence-based decisions, and recoverable handover notes. - Ability to manage working-context limits, preserve unfinished work, respect permissions, and distinguish active processes from verified outcomes. - Ability to assess system capacity, review paths, model account limits, and operational cost as team activity scales. - Demonstrated discipline in identifying and removing the root causes of recurring failures. - Hands-on experience with AI Coding Assistants, AI Agent Frameworks, Command Line, Test Automation, AI Output Evaluation, Incident Diagnosis, Workflow Automation, Release Verification. Skills - AI Coding Assistants - AI Agent Frameworks - Software Engineering - Git - Shell Scripting - Command Line - macOS - Desktop Automation - Test Automation - AI Output Evaluation - Incident Diagnosis - Workflow Automation - Release Verification - automation - Translate business priorities into clear outcomes, written task briefs, scope boundaries, and measurable definitions of success. - Coordinate parallel AI engineering workstreams, shared code, technical decisions, and dependencies. - Configure AI coding tools, terminal sessions, and management automation while keeping objectives, progress, and handoffs visible. - Monitor AI team managers, respond to questions, and recover interruptions without losing evidence or creating duplicate ownership. - Inspect technical changes and tests, require appropriate review, and oversee safe source integration, releases, and real-world verification. - Evaluate AI output through source review, meaningful tests, and quality checks rather than relying on automated summaries. - Protect confidential information and access boundaries, and escalate decisions beyond the role's authority to the appropriate owner. - Assess capacity across machines, review paths, and model accounts, expanding activity based on measured demand and established limits. - Investigate recurring failures and remove their underlying causes so operating methods remain simple as they scale. - Maintain written intent, ownership, and handoffs so work remains recoverable when sessions fail or stall. - Concurrent Development Teams - Evidence-Driven Delivery - Agent Orchestration - Capacity Planning
Наблюдалась 2026-10-12, впервые 2026-10-12, источник — Get on Board (LATAM).