Hippocratic AI

Performance Engineer

Menlo ParkfulltimemidAdded today

About this role

Hippocratic AI seeks a Performance Engineer to establish performance standards across their healthcare AI platform. You'll build automated testing frameworks, monitor VoIP quality metrics, and partner with engineering teams to optimize a full-stack system handling LLM inference, microservices, and real-time communications.

What you'll do

Design and maintain automated performance testing frameworks for LLM inference, REST/gRPC microservices, and infrastructure components
Integrate performance tests into CI/CD pipelines to catch latency and throughput regressions before deployment
Define SLIs/SLOs and build dashboards for real-time system health visibility
Measure and track VoIP quality metrics (MOS, jitter, packet loss, latency) using synthetic call load testing
Correlate audio degradation signals with infrastructure metrics to identify root causes
Drive performance culture by partnering with cross-functional teams and leading incident reviews

What they're looking for

Performance engineering and automated test harness development (Locust, k6, Gatling, JMeter)
PostgreSQL tuning (execution plans, indexing, connection pooling, autovacuum)
Redis optimization (eviction policies, clustering, pipelining)
Observability tools (Prometheus, Grafana, CloudWatch)
VoIP/Telephony protocols (SIP, RTP/RTCP, RTCP-XR) and testing tools (SIPp)
Distributed systems fundamentals (queueing theory, tail latency, backpressure)
ML inference server benchmarking (vLLM, TensorRT-LLM, Triton)
Kubernetes profiling and chaos engineering

Likely interview questions

Walk us through your experience building automated performance test harnesses. What tools have you used, and how did you integrate them into CI/CD pipelines to catch regressions?
Describe a time you diagnosed and resolved a latency or throughput issue in a distributed system. What metrics and tools did you use, and how did you validate the fix?

Tell us about your experience tuning PostgreSQL and Redis for production workloads. What optimization techniques have proven most impactful for you?
Have you worked with VoIP or telephony systems? Walk us through how you'd approach measuring and diagnosing audio quality degradation across network, codec, and application layers.
How do you approach defining SLIs/SLOs for a complex system, and how have you used observability tools like Prometheus or Grafana to operationalize them across teams?
Describe your experience with ML inference performance benchmarking. Have you worked with systems like vLLM or Triton, and how would you characterize their performance bottlenecks?
Tell us about a situation where you had to influence multiple engineering teams (ML, backend, infra) around performance priorities. How did you present data and build consensus?

Unlock all 7 questions free — and practice them live →

Apply on the employer's site →

Opens the official application on the employer’s site. No login required.