AI architect

Role Overview

We are seeking an AI Tech Lead to architect and implement real-time AI systems, including LLM pipelines, voice automation, and knowledge-enhanced applications. The candidate should have strong hands-on AI/LLM experience and the ability to define best practices, scalable architectures, and system KPIs.

Key Responsibilities

Lead design of distributed, provider-agnostic AI architectures (multi-LLM, STT/TTS, microservices).

Define best practices for GenAI systems, including prompt design, safety patterns, caching, and falover logic.

Own LLM evaluation, routing, and performance benchmarking, ensuring low latency, reliability, and cost efficiency.

Build and optimize RAG/knowledge integration, vector DB retrieval, and context enhancement pipelines.

Ensure data security and compliance for voice, transcript, and contextual data.

Mentor small AI teams (36 engineers) and guide technical implementation.

Required Skills

8+ years in software engineering, distributed systems, or AI platforms.

3+ years hands-on experience with LLM/GenAI systems in production.

Strong knowledge of:

LLMs & prompt engineering

Real-time/streaming systems

Microservices and scalable architectures

Cost-aware system design & AI safety fundamentals

Excellent communication and collaboration skills.

Preferred Skills

Experience with vector DBs (Pinecone, Weaviate, FAISS, OpenSearch)

Cloud platforms: AWS, Azure, GCP

Streaming & messaging systems (Kafka, Pub/Sub)

Voice AI or agentic workflow experience