AI Tech Lead

Role Overview

We are hiring a senior AI Tech Lead to architect and guide the implementation of real-time, production-grade GenAI systems, with a strong focus on voice automation, LLM orchestration, and knowledge-grounded AI applications.This role requires deep hands-on expertise in low-latency AI systems, architectural judgment, and the ability to define technical standards for scalable, reliable, and cost-efficient AI products.Time Zone: IST with 23 hours overlap with PST

Key ResponsibilitiesAI & System Architecture

Design and lead implementation of distributed, provider-agnostic AI architectures, including:o Multi-LLM provider setupso STT , LLM, TTS pipelineso Microservices-based AI platformsEnsure low speech-to-speech latency, high availability, resilient failover, and efficient scaling.Define architectural best practices and dos and donts for GenAI systems.LLM Orchestration & GovernanceOwn evaluation, selection, and routing strategies across multiple LLM providers.Design prompt architectures, safety patterns, fallback logic, caching, and context shaping.Optimize context windows, token usage, inference latency, and overall cost.Continuously assess new models and emerging GenAI capabilities.Knowledge Integration & RAGArchitect and own RAG and knowledge-grounding systems, including:o Vector databases and retrieval strategieso Chunking and indexing policieso Hybrid retrieval and grounding approacheso Function calling and knowledge graph integrationsEnsure retrieval quality supports accurate, safe, and domain-grounded responses.Performance, Quality & ReliabilityDefine and track KPIs for:o LLM output quality and grounding accuracyo Latency and throughputo Reliability and system stabilityEstablish benchmarking and evaluation frameworks for AI components.Data Security & Multi-TenancyEnsure responsible handling of voice and transcript data.Apply PII-safe practices and support data retention and isolation in multi-tenant environments.Technical LeadershipProvide technical direction and mentorship to engineering teams.Review system designs and make key architectural decisions.Stay hands-on with critical system components and prototypes.

Required Qualifications

• 8-12 years of experience in software engineering, with significant ownership of backend or platform systems
• Strong hands-on experience building production LLM-based systems
• Proven experience with real-time or low-latency systems, preferably involving voice or streaming data
• Deep understanding of distributed systems, microservices, and scalable architectures
• Practical experience with RAG systems, vector databases, and retrieval optimization
• Strong problem-solving skills with a focus on performance, reliability, and cost efficiency.

Nice to Have

• Experience with conversational AI or voice automation platforms
• Exposure to multi-tenant SaaS architectures
• Knowledge of function calling, agent orchestration, or knowledge graphs
• Experience working with globally distributed teams.