Principal Software Engineer - AI Platforms & Communications

View full description

Requirements:

• 10+ years building distributed, customer‑facing systems; 3+ years designing ML or LLM production workloads at scale.
• Proven success with LLMs, RAG architectures, vector databases (e.g., Pinecone, Weaviate, PG Vector), embedding models, and fine‑tuning techniques.
• Deep knowledge of multi‑tenant SaaS patterns, data isolation, and usage‑based cost modeling.
• Fluency in at least one of Go, Python, or Java (Go/Python preferred) plus modern cloud stacks (GCP or AWS).
• Experience integrating or operating communications stacks—SIP/WebRTC for voice, SMS gateways, and transactional email services.
• Expertise in Kubernetes, IaC/GitOps, observability, and CI/CD for high‑compliance environments (HIPAA/PCI).
• Track record of shipping large, cross‑org initiatives on time and mentoring others to do the same.

Responsibilities:

• Set architecture & strategy for multi‑tenant, AI‑powered communications services (voice, SMS, email).
• Design and build RAG pipelines, vector‑store–backed retrieval layers, and fine‑tuning workflows that deliver low‑latency, context‑aware experiences.
• Lead end‑to‑end platform initiatives: data ingestion, event processing, model hosting, continuous evaluation, and cost/latency optimization.
• Champion best practices for LLM safety, prompt management, experiment tracking, observability, and auto‑scaling.
• Influence roadmaps across Product, Design, and multiple engineering squads; unblock teams with reusable SDKs, templates, and reference architectures.
• Mentor & level‑up senior and staff engineers; foster a culture of ownership, experimentation, and inclusive collaboration.