Performance Engineer

About the Company

Hippocratic AI is the leading generative AI company in healthcare. We have trained our own LLMs as part of our Polaris constellation, resulting in a system with over 99.9% accuracy, designed to transform patient outcomes at a global scale.

Responsibilities

• Design and maintain automated performance testing frameworks covering LLM inference, microservices, and infrastructure (PostgreSQL, Redis, message queues)
• Integrate performance suites into CI/CD to gate deployments against latency and throughput regressions
• Define SLIs/SLOs and build real-time visibility dashboards using tools like Grafana
• Measure and track VoIP quality metrics including MOS scores, jitter, packet loss, and latency
• Build synthetic call load testing infrastructure to stress telephony paths at scale
• Partner with ML, Speech, Backend, and Infra teams to prioritize performance-related engineering work

Requirements

• BS in Computer Science or equivalent
• 10+ years in performance engineering with software development and SRE background
• Proven track record building automated performance test harnesses (Locust, k6, Gatling, or JMeter)
• Deep experience with PostgreSQL performance tuning and Redis optimization
• Solid grasp of distributed systems fundamentals including queueing theory and tail latency
• Fluency with observability tools such as Prometheus, Grafana, or Cloudwatch
• Working knowledge of VoIP/Telephony protocols including SIP, RTP/RTCP, and RTCP-XR
• Hands-on experience with VoIP testing tools like SIPp
• Familiarity with MOS scoring methodologies (PESQ, POLQA, or E-model)

Preferred Qualifications

• Experience benchmarking ML inference servers like vLLM, TensorRT-LLM, or Triton
• Kubernetes workload profiling and resource right-sizing
• Chaos engineering experience with tools like Toxiproxy or Gremlin
• Background in healthcare tech or high-reliability, latency-sensitive systems