We're Hiring: AI Tech Lead (Real-Time AI & GenAI Systems)
We are looking to hire a
strong AI Tech Lead
who can architect and guide the implementation of
real-time AI systems
across
voice automation, LLM pipelines, and knowledge-enhanced applications
.
This role demands deep architectural judgment, hands-on expertise with
LLMs and GenAI
, and the ability to define
best practices, performance benchmarks, and scalable system designs
for low-latency, production-grade AI products.
Role Overview
As an
AI Tech Lead
, you will lead the design and development of
distributed, provider-agnostic AI architectures
involving multi-provider LLMs, speech pipelines (STT/TTS), and AI microservices. You will be responsible for ensuring
low latency, high reliability, scalability, and cost efficiency
across real-time AI systems.
You will also set technical standards, guide engineers, and make high-impact architectural decisions for enterprise and customer-facing AI products.
Key Responsibilities
AI Architecture & Systems Design
Architect and lead development of real-time AI systems including:
Multi-provider LLM pipelines
Speech-to-text (STT) and text-to-speech (TTS) chains
Distributed AI microservices
Ensure low speech-to-speech latency, resilient failover, load balancing, and horizontal scaling
Design provider-agnostic architectures with intelligent routing and fallback strategies
Optimize inference paths for performance and cost efficiency
GenAI Best Practices & Governance
Define architectural "dos and don'ts" for GenAI systems:
Prompt design and safety patterns
Context shaping and window optimization
Caching and fallback logic
Real-time agent orchestration
Lead model governance and evaluation frameworks:
Benchmarking multiple LLM providers
Routing logic based on latency, quality, and cost
Token efficiency and context management
Establish KPIs for:
LLM quality and grounding accuracy
Latency and reliability
Cost control and system stability
Knowledge & RAG Architecture
Own end-to-end
RAG and knowledge integration architecture
Design and optimize:
Vector databases and retrieval strategies
Chunking and embedding policies
Context enhancement and hybrid grounding approaches
Function calling, tool use, and emerging knowledge-graph integrations
Ensure retrieval quality supports accurate, safe, and domain-grounded responses
Security & Data Handling
Ensure secure handling of voice and transcript data
Apply basic PII-safe practices and data isolation
Support retention, deletion, and multi-tenant data controls
Technical Leadership
Provide technical guidance and mentorship to AI engineers
Define performance benchmarks, design standards, and review practices
Stay ahead of new LLM capabilities, voice AI trends, and GenAI tooling
Required Skills & Experience
Strong experience designing and building
production-grade AI systems
Deep hands-on expertise with
LLMs, RAG, and GenAI architectures
Experience with real-time or low-latency systems (voice AI preferred)
Strong understanding of distributed systems, microservices, and scaling patterns
Experience working with multiple LLM providers and routing strategies
Ability to balance
quality, latency, reliability, and cost
Strong architectural thinking and decision-making skills
Nice to Have
Experience with voice automation platforms and conversational AI
Exposure to function calling, tool-using agents, and knowledge graphs
Prior experience defining AI governance or platform standards
Experience in multi-tenant SaaS AI platforms
What You'll Get
Ownership of core AI architecture decisions
Opportunity to build and scale real-time AI systems used in production
Work on cutting-edge voice AI, LLM, and knowledge-grounded applications
Influence long-term AI platform strategy and technical direction
Collaborate with senior engineers, product leaders, and founders