Senior Recommendation System Engineer

About the role

This role owns the end-to-end lifecycle of large-scale recommendation systems for a global user base. You will drive architecture, real-time data pipelines, and model inference for multi-channel ranking pipelines. The work directly supports Bybit's trading, payments, and Web3 products at internet scale.

Software engineers turn product ideas into working code. Engineers work in small teams, review each other's work, and ship in small batches. Most teams follow agile practices such as sprints and daily standups. Engineers also write tests, fix bugs, and improve performance. The field values clear communication as much as technical skill. Engineers spend part of every week on planning, code review, and debugging, not just writing new code. The ability to explain a technical decision in plain words separates strong engineers from the rest.

Key facts

What you'll do

Multi-stage recommendation engines are built and refactored to achieve low latency at high concurrency across recall, coarse ranking, fine ranking, and re-ranking stages.

Dynamic compute trimming and degradation strategies are implemented to sustain core engine stability during extreme traffic spikes for personalized global strategy dispatch.

Requirements

Five or more years of hands-on recommendation system engineering are required at consumer-scale internet companies with proof of participating in or leading architecture refactoring or launches serving tens of millions of users.

Low-level computer science fundamentals are mastered, and proficiency in at least one of Go, Java, or C++ is required, with Go preferred and C++ experience a plus for future engine optimization.

Deep hands-on experience with Spark, Flink, and Kafka is necessary, including real-time stream computing latency and data backlog resolution, plus Milvus or Faiss cluster deployment and tuning.

Deep understanding of computational complexity and online bottlenecks for collaborative filtering, two-tower recall, and multi-objective optimization MMoE/PLE is required to interface effectively with algorithm teams.

Proven experience designing and building recommendation platforms, feature platforms, experimentation platforms, or high-performance RPC frameworks at top-tier companies is required.

Practical notes

This role targets consumer-scale internet products and infrastructure under high-performance and high-availability constraints.

Typical interview steps

Hiring for engineering roles usually starts with a recruiter screen, followed by one or two technical rounds. Candidates often solve a coding problem, discuss past projects, and answer system design questions. Some loops include a take-home task. Final rounds typically cover team fit and give candidates a chance to ask questions. Interviewers look for how you break down an unfamiliar problem, not just whether you reach the answer. Practicing a few problems aloud and reviewing your own past projects are the best preparation.

Good to know

Recommendation systems combine collaborative filtering, embedding retrieval, and multi-objective deep models to rank content and products.

Large-scale vector databases and distributed stream processing define real-time personalization infrastructure.

System design for high concurrency, low latency, and graceful degradation is central to this role.

Global observability relies on distributed tracing and experiment platforms to drive rapid iteration.

Questions to ask

Good questions to ask the employer in the interview: what does success look like in the first six months, how is the team structured, what is the current biggest challenge, and how are decisions made. Asking about growth paths and the review process is also well received. Employers expect questions, and good ones show preparation.

Career growth

Engineering careers usually progress from individual contributor to senior, staff, and principal levels. Some engineers move into management and lead teams of five to twenty people. Others stay on the technical track. Growth follows demonstrated impact, not tenure alone. A typical engineering ladder has clear levels with defined expectations for scope, quality, and mentorship. Moving up usually requires owning outcomes end to end rather than completing assigned tickets.