Software Engineer, Inference

Highlights

• Own a production model-serving service end-to-end from design to ops.
• Improve latency and throughput for real-time generative AI applications.
• Shape an industry-defining inference platform powering demanding AI workloads.

What they offer

• 100% employer-paid medical, dental, and vision
• 401(k) with a generous employer match
• Flexible PTO
• Discretionary bonus and equity awards
• Paid parental leave
• Catered lunch in office locations

Ideal candidate

Early-career builder who loves owning services end-to-end and sweating tail latency. You care about reliability, operational excellence, and turning powerful infrastructure into seamless AI experiences.

Requirements

• 0-3 years of software engineering experience building cloud/distributed services in production
• Proficiency in Python or Go with gRPC/HTTP APIs and containerized deployments
• Working knowledge of Kubernetes (or Slurm/Ray) and CI/CD pipelines
• Experience with metrics/alerting (Prometheus/Grafana/OpenTelemetry) and structured logging
• Basic understanding of GPU inference concepts (KV caching, mixed precision, streaming tokens)