Backend / Infra Engineer
About the role
Backend/Infra Engineer role at Hamming AI focused on owning reliability and scale for real-time, LLM-enabled voice agent platform. Responsible for core services, observability, and infrastructure readiness to support high concurrency and 99.99% uptime.
Responsibilities
- Own core services in TypeScript/Node.js and Python orchestrating LiveKit, Temporal, STT/TTS, and LLM tooling for real-time voice agents.
- Scale 1 → N → 100×: harden systems for 10K parallel calls with 99.99% uptime.
- Harden pipelines for ingestion, evaluation, and analytics so telephony events, recordings, and outcomes propagate reliably across services.
- Level-up observability with OpenTelemetry/SigNoz and trace-first practices to shrink MTTR in prod.
- Prototype → test → prod: ship new LLM-driven behaviors with measurable success metrics, guardrails, and CI regressions.
- Infrastructure readiness: CI/CD, environment automation, incident response playbooks—keep customer conversations online.
Qualifications
- 3+ years of experience
- Senior/Staff experience with distributed backends under real-time/streaming constraints
- Fluent in TypeScript/Node.js; comfortable with Python for ML/audio tasks
- Knowledge of Temporal (or similar workflow engines), queues, Redis, PostgreSQL
- Production experience with LLM apps; understanding of prompt/tool design, evals, guardrails
- Cloud-native on AWS with Terraform; comfortable with Kubernetes
- Experience with Cursor/Zed/Devin and code-generation workflows (bonus)
- Ability to work independently, engage with customers, and maintain quality
- Bonus: experience building real-time systems in Telecom/Networking, Autonomous Vehicles, or HFT; founder experience; AI voice apps
Skills
Benefits
- Not specified in description
About Hamming AI
Automated voice AI agent testing and monitoring
Hamming automates the QA of voice agents. (both pre-deployment testing and post-deployment analytics) Making voice AI agents reliable is hard. A small change in prompts, function call definitions, or model providers can cause large changes in LLM outputs. We have a proven track record of helping enterprises win with AI. Sumanyu (CEO) previously helped Citizen (safety app) grow its users by 4X and grew an AI-powered sales program to 100s of millions in revenue/year at Tesla. Our eng team ranks #1 on https://workweave.ai/
More open roles at Hamming AI
- Product Engineer11mo agoSan Francisco, CA · Engineering