Staff Software Engineer (Infrastructure )

Навыки

• Avro / Parquet
• AWS
• BigQuery
• ClickHouse
• Многопоточность
• C++
• Отладка и поиск ошибок

О компании и продукте

• Every AI insight, every experiment, every cohort at Amplitude starts with a query. Our in-house OLAP engine, Nova , processes trillions of events in real time — turning raw behavioral data into fast, trustworthy answers that power decisions for thousands of product teams worldwide.
• We’re entering a world where AI agents don’t just assist product teams — they ship features, run experiments, and make prioritization calls autonomously. What makes that possible is agents’ ability to verify their work against real product data continuously. That makes Nova the critical infrastructure in the loop, and as non-stop agents become the main source of queries, the demand on Nova’s throughput, correctness, and operational rigor grows dramatically.
• We’re looking for a Staff Software Engineer who wants to go deep on both the engine internals and the infrastructure underneath it. You’ll work across the full stack of a modern OLAP system — query planning and execution, columnar storage and encoding, distributed compute, caching, and cloud infrastructure — while driving meaningful improvements to performance, cost-efficiency, and reliability at scale. You’ll influence technical direction through your work, your design reviews, and your mentorship of other engineers on a team of ~10.
• This role is ideal for someone who finds real satisfaction in making a complex distributed system faster, cheaper, and more reliable — and who wants to do that work on a system that directly powers the product experience for thousands of customers.

Задачи

• Build and evolve core query engine infrastructure
• Work across Nova's query execution engine and distributed compute layer: query planning, columnar storage formats, encoding and compression, caching, and cluster-level resource management
• Design and implement new capabilities as Nova expands to support more warehouse-imported data types, such as metrics, profiles, and dimensions
• Design for high-throughput automated query workloads — as AI agents become a primary source of queries, ensure Nova’s architecture supports sustained, concurrent, and programmatic query patterns at scale
• Drive cost and performance at scale
• Own and execute projects that materially reduce infrastructure cost — compute, storage, network, and memory — while maintaining or improving latency and throughput
• Profile and optimize JVM performance: GC tuning, memory management, concurrency, and data layout decisions that compound at our scale
• Build guardrails and observability to catch expensive or pathological queries before they impact the system
• Improve reliability and operational excellence
• Strengthen Nova’s reliability posture: identify systemic failure modes, drive durable fixes, and raise the bar on how we detect and respond to production issues
• Participate in on-call rotation to root-cause incidents and turn one-off fixes into architectural improvements
• Contribute to capacity planning, safe rollout practices, and the operational tooling that keeps Nova healthy
• Influence through technical leadership
• Lead the design and execution of multi-month projects that improve Nova’s architecture, performance, or capabilities
• Contribute to technical direction through design docs, architecture discussions, and code reviews — helping the team make principled tradeoffs
• Mentor senior engineers on distributed systems thinking, production debugging, and system design
• Collaborate with Product, Middleware, Data Pipeline, and other engineering teams to ensure Nova’s capabilities translate into customer value

Требования

• You are an experienced systems engineer who
• Gets energy from working deep inside a complex distributed system — understanding how data flows through it, where the bottlenecks are, and how to make it meaningfully better
• Has built or significantly extended an OLAP engine, columnar database, query processor, or large-scale data processing system — not just operated one
• Thinks about cost, performance, and reliability as interconnected concerns, not separate workstreams
• Communicates clearly about technical tradeoffs and earns influence through the quality of your work and ideas, not through title
• Finds it natural to help other engineers level up — through pairing, design reviews, or just being the person who explains the “why” behind a system’s design
• 7+ years of industry experience in backend or infrastructure engineering, with depth in distributed data systems
• Hands-on experience building or extending analytical/OLAP systems — query engines, columnar storage, large-scale data processing frameworks, or equivalent
• Track record of driving significant cost optimization on cloud infrastructure at scale (compute, storage, network)
• Strong computer science fundamentals: distributed systems (partitioning, replication, consistency, failover), data structures and algorithms, concurrency and multi-threading, performance optimization
• Production experience with modern cloud infrastructure — AWS (S3, DynamoDB, EC2), Kafka, Redis/ElastiCache, Kubernetes, Terraform — or strong equivalents
• Proficiency in Java, C++, or Python
• Demonstrated technical influence beyond your immediate team: leading design discussions, driving cross-team alignment, mentoring engineers

Будет плюсом

• Experience with specific OLAP or query engine systems: Druid, ClickHouse, Presto/Trino, BigQuery, Snowflake, or similar
• Deep JVM expertise — GC tuning, profiling, memory optimization at production scale
• Experience with columnar data formats and encodings (Arrow, Parquet, ORC, or custom formats)
• Familiarity with product analytics, experimentation platforms, or event-driven data systems
• Contributions to open-source data infrastructure projects or published work in the data systems space

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.