Architect (Generative AI)

Location: Hybrid work from the TLV office; work from anywhere is available for up to 2 weeks per year.

Company

hirify.global provides an Agentic Care Communications platform that uses HIPAA-compliant AI agents to automate healthcare workflows and conversations across call centers, websites, SMS, mobile apps, and other channels.

What you will do

• Own end-to-end architecture across teams, write and review design documents, set technical standards, and make cross-team trade-offs explicit.
• Define model strategies covering model size, hosting, fine-tuning, distillation, routing, provider fallback, quality, latency, and cost.
• Design serving infrastructure for small and large models with strict latency and availability targets.
• Build evaluation, anomaly-detection, classification, guardrail, hallucination-control, and explainability systems for healthcare-grade agents.
• Design low-latency, high-accuracy voice and multi-channel experiences, lead AI initiatives, and integrate third-party systems.
• Write production code, build prototypes, own critical agent services, mentor senior engineers, and raise review standards.

Requirements

• 5+ years of experience as an architect or principal engineer, including 2+ years building ML or LLM-based applications in production.
• Bachelor’s or master’s degree in computer science, data science, or a related field.
• Hands-on Python experience and willingness to write production code and prototypes; Node/TypeScript is a plus.
• Deep production experience with LLM systems, including context engineering, RAG, tool calling, structured outputs, and agent frameworks such as LangGraph or similar.
• Experience designing evaluation frameworks for non-deterministic systems and using them to make shipping decisions.
• Experience with real-time, latency-sensitive systems, including streaming, WebSockets or WebRTC, and event-driven architectures.
• Ability to switch between quick 0-to-1 builds and hardening platforms at scale.
• Strong interpersonal, leadership, and communication skills in a fast-changing environment.

Nice to have

• Knowledge of MLOps.
• Voice AI experience with STT/TTS, speech-to-speech models, LiveKit, or similar technologies.
• Model serving and optimization experience with vLLM/Triton, quantization, GPU efficiency, or fine-tuning small models.
• Experience with LLM observability tools such as Langfuse or similar.

Culture & Benefits

• Hybrid, dog-friendly TLV office.
• Unlimited PTO and paid sick leave.
• Company-wide long weekends every quarter.
• Pension, social benefits, Keren Hishtalmut, and a monthly meal allowance.
• Work from anywhere for up to 2 weeks per year.