Sr Backend Engineer

You’ll bring strong backend and data engineering fundamentals - pipeline design, orchestration, data modeling, and service/API development - with enough exposure to embeddings, vector search, and ML-adjacent concepts to support our hybrid (lexical + vector) retrieval today and our move toward ranking and relevance improvements tomorrow. You’ll work at the intersection of data infrastructure, backend services, and search, ensuring our indices are fresh and our retrieval services are performant, reliable, and built to support increasingly sophisticated search., To support collaboration, we ask employees to be in the office at least two days a week: Wednesday and Thursday., * Design, build, and maintain data pipelines that ingest, transform, and load content into Elasticsearch indices at scale.

• Own index design - mappings, analyzers, sharding strategy, and lifecycle management - balancing indexing throughput, query latency, and storage cost.
• Build and operate the infrastructure for hybrid retrieval, combining lexical (BM25) search with dense vector similarity (kNN/HNSW) in Elasticsearch.
• Design and maintain the backend retrieval/query services that sit in front of Elasticsearch - API design, request routing, caching, and query fan-out.
• Integrate embedding generation into pipelines - batching, caching, and re-embedding workflows when models or content change - using off-the-shelf or hosted embedding models.
• Partner with product and applied ML teams to support the evolution from retrieval into multi-stage ranking, including feeding features to future learning-to-rank systems.
• Monitor and troubleshoot cluster health, service latency, indexing throughput, and query performance; drive improvements in reliability and observability.
• Implement zero-downtime reindexing and index cutover strategies (aliasing, blue/green indices) to support continuous schema and data evolution.
• Establish data quality and validation practices to catch pipeline failures and indexing issues before they reach production.
• Collaborate with infrastructure/platform teams on cluster sizing, service scaling, and cost optimization.
• Support experiment rollout for retrieval and ranking changes, working with feature flagging or A/B test infrastructure.
• Stay current on Elasticsearch/OpenSearch and retrieval-infrastructure best practices, evaluating what’s worth adopting.

• Minimum 4+ years of experience in backend or data engineering, with hands-on ownership of production data pipelines and/or backend services.
• Strong SQL and experience with data warehouses (Snowflake, BigQuery, Redshift, or similar).
• Proficiency in Python (or Java/Scala) for pipeline and service development, and experience with orchestration tools (Airflow, Dagster, Prefect, or similar).
• Experience with dbt for data transformation, modeling, and testing within the warehouse.
• Hands-on experience with Elasticsearch or OpenSearch in production - index design, mappings, ILM, sharding, and cluster tuning.
• Experience designing and operating backend services/APIs (REST or gRPC) - request handling, caching, and performance optimization for low-latency, read-heavy systems.
• Experience with service observability - tracing, metrics, and alerting (Datadog, Prometheus/Grafana, or similar).
• Comfort with containerization and deployment (Docker, Kubernetes) for production services.
• Clear, effective communication, with the ability to collaborate well with data scientists, ML engineers, and product partners.
• Comfort operating in cloud infrastructure (AWS/GCP/Azure), including cost and performance tradeoffs for search infrastructure., * Experience with batch and/or streaming data processing (Spark, Kafka, Flink, or similar).
• Practical experience with vector search - dense_vector fields, kNN/HNSW, and combining lexical and vector scores for hybrid retrieval.
• Working familiarity with embedding models (open-source or hosted/API-based) - generating, storing, versioning, and refreshing embeddings at scale.
• Understanding of retrieval evaluation basics (recall@k, NDCG, MRR).
• Experience with learning-to-rank libraries (e.g., LightGBM, XGBoost rankers) or exposure to reranking pipelines.
• Experience with reciprocal rank fusion (RRF) or other hybrid score-blending techniques.
• Familiarity with vector databases beyond Elasticsearch (FAISS, ScaNN, pgvector, etc.).
• Prior experience scaling search/retrieval infrastructure in a high-traffic consumer or enterprise product.

4.74.7 out of 5 stars New York, NY Hybrid work $167,000 - $219,000 a year - Full-time, Pulled from the full job description

• 401(k) matching
• Paid time off
• Vision insurance
• Health savings account
• Dental insurance
• Family leave
• Flexible spending account, * Collaborate with your manager and team to create a healthy work-life balance
• 20 vacation days that we expect you to take!
• Competitive health, dental, and vision insurance (100% employee and 75% dependent PPO, Dental, VSP Choice)
• Employer-sponsored 401k plan with company match
• Access to LinkedIn Learning and other resources to support professional growth
• Paid Family Leave, FSA, HSA, Commuter benefits, and Wellness benefits
• 40 hours of annual paid time off to participate in volunteer programs of choice

We strive to make everyone feel comfortable and welcome!

We work to create a holistic interview process, where both Quizlet and candidates have an opportunity to view what it would be like to work together, in exploring a mutually beneficial partnership.

We provide a transparent setting that gives a comprehensive view of who we are!

In Closing:

At Quizlet, we’re excited about passionate people joining our team-even if you don’t check every box on the requirements list. We value unique perspectives and believe everyone has something meaningful to contribute. Our culture is all about taking initiative, learning through challenges, and striving for high-quality work while staying curious and open to new ideas. We believe in honest, respectful communication, thoughtful collaboration, and creating a supportive space where everyone can grow and succeed together.”

Quizlet’s success as an online learning community depends on a strong commitment to diversity, equity, and inclusion., Compensation Range: $167K - $219K

At Quizlet, our mission is to help every learner achieve their outcomes in the most effective and delightful way. We’re a $1B+ learning platform used by two-thirds of U.S. high school students and half of college students, powering over 1 billion learning interactions each week.

We blend cognitive science with machine learning to personalize and enhance the learning experience for students, professionals, and lifelong learners alike. We’re energized by the potential to power more learners through multiple approaches and various tools.

Let’s Build the Future of Learning

Join us to design and deliver AI-powered learning tools that scale across the world and unlock human potential.