Senior Performance Engineer

Навыки

• AppsFlyer / Adjust
• AWS
• CI/CD
• Многопоточность
• Datadog / New Relic
• Распределённые системы
• ELK / Elastic Stack

Задачи

• Go/No-Go decisions with our stakeholder about launches services before integrating them into our ecosystem and integrations support (audit APIs, web, databases, caches, message brokers)
• Design&Execute Load Tests global strategy
• Modeling of load testing scenarios (load, stress, soak, peak, find max tests), methodology and formation of non-functional requirements for system using k6, JMeter (DSL framework)
• Simulate real-world scenarios and traffic patterns to validate systems under production-like conditions (including high RPS, concurrency levels, data skew, and geo-distributed load)
• Load Modeling
• Calculate and validate detailed load models – e.g. expected RPS, concurrent users, transaction volumes, and data distribution
• Adjust these models to mirror peak and edge-case scenarios, ensuring our capacity planning is grounded in reality
• Bottleneck Analysis & Fixes
• Find, analyze, and fix performance bottlenecks. This includes
• backend issues (CPU hotspots, memory leaks, GC pauses, thread pool exhaustion)
• DB inefficiencies (Aurora MySQL/RDS indexing, query locks, IOPS limits)
• messaging/queue back-pressure (Kafka partitioning, consumer lag, throughput limits)
• network constraints (latency, load balancer settings, timeouts)
• Work hands-on with SRE, DevOps, and Backend teams to implement optimizations and verify the improvements
• Prepare for Production Traffic
• Ensure services are production-ready
• Drive capacity planning exercises and stress tests to determine scaling lag/limits and failure modes
• Verify that services can gracefully handle traffic spikes or component failures without violating SLAs or SLOs
• Help partners configure autoscaling policies for sustained performance
• Loadtesting Infrastructure Setup&Tuning
• Set up, audit, and operate performance testing infrastructure for our services load testing automation and geo-distributed load generator to simulate production traffic
• Approach performance issues with an performance analyst/architect mindset – form hypotheses, design experiments, run tests, and draw conclusions to configuration infrastructure and fix backend code
• For example, if latency is high, hypothesize the cause (e.g. database index missing), test the hypothesis, and then make a the fix
• Repeat this iterative process to methodically improve system performance
• Business Impact Translation

Условия

• Employment Type: Full Time
• Location: Kazakhstan

Паспорт вакансии

История публикации

Откуда что взялось

Отмечено то, что вывели мы. Без пометки — значение назвал работодатель.

Почему на этом месте в выдаче

Порядок выдачи объявлен контрактом: свежесть решает между днями, полнота и зарплата — внутри дня.