AI Engineer

Responsibilities:

• Architect and operate end-to-end AI systems for conversational interfaces and speech recognition.
• Build production agent workflows: orchestration, memory, and retrieval.
• Run self-hosted serving (vLLM, Triton class) and own latency, throughput, and cost per user.
• Design LLM gateway routing, rate limits, and fallbacks, and drive accuracy vs. cost trade-offs with ground-truth metrics and eval harnesses.

Requirements:

• 4-8 years as an AI/ML engineer with production systems behind you.
• A 01 track record: founding engineer, early team member, or someone who built a system from scratch.
• Agentic AI in production, self-hosted model serving, and LLM gateway experience.
• Python fluency, strong CS foundations (top-tier institute background preferred), and metric-first thinking.
• Bonus: speech-to-text and diarization, Kubernetes on GCP.