We're looking for a Senior Backend Engineer to own the services and APIs that power the data layer. You'll design the systems that ingest, evaluate, and serve agent telemetry at scale.
What You'll DoDesign and build high-throughput backend services that ingest and process hundreds of thousands of agent traces per second.
Own the API surface our SDKs and dashboards depend on: define contracts, manage versioning, and keep latency low under real customer load.
Tune our OLAP layer (ClickHouse) through schema design, query optimization, and access-pattern analysis so reads stay fast as data grows to petabyte scale.
Partner with the platform and infra teams on scalability, reliability, and the systems that back our evaluation and monitoring pipelines.
Advocate for a high bar on backend and engineering quality: reliable, efficient, well-documented, testable, and maintainable.
6+ years of relevant industry experience building and operating high-throughput backend systems and services.
Strong fundamentals in API design, data modeling, and the trade-offs of distributed systems under real production load.
Hands-on experience with OLAP / columnar databases (ClickHouse, Presto) and a feel for how query patterns map to storage internals.
Experience designing high-performance distributed systems.
Comfort across the stack, with the breadth to reason about platform and infra decisions.
Strong communication skills. You write clearly, review well, and make the people around you better.
Experience scaling pipelines that fan out to LLM APIs and managing the rate-limit, retry, and cost dynamics that come with them.
Familiarity with streaming systems (Kafka, Spark, Flink, Ray) and ML orchestration tools (Airflow, Dagster, Prefect).
Background in embedding / vector search infrastructure or data quality monitoring.
Prior work on observability or developer-facing platform products.
Skills Required
- 6+ years building and operating high-throughput backend systems and services
- Strong fundamentals in API design, data modeling, and distributed systems trade-offs
- Hands-on experience with OLAP / columnar databases (ClickHouse, Presto)
- Experience designing high-performance distributed systems
- Comfort across the stack to reason about platform and infra decisions
- Strong written and verbal communication skills
- Experience scaling pipelines that fan out to LLM APIs (rate-limit, retry, cost dynamics)
- Familiarity with streaming systems (Kafka, Spark, Flink, Ray)
- Familiarity with ML orchestration tools (Airflow, Dagster, Prefect)
- Background in embedding / vector search infrastructure or data quality monitoring
- Prior work on observability or developer-facing platform products
What We Do
Judgment Labs builds agent behavior monitoring (ABM) infrastructure. Judgment provides a toolkit to track and judge agent behavior in online and offline setups, enabling you to convert high-signal interaction data from production/test environments into more reliable agents.
.png){kind=logo}
