AI Architect

We are seeking an experienced AI Architect to design, build, and scale production-ready AI voice conversation agents deployed locally (on-prem / edge / private cloud) and optimized for GPU-accelerated, high-throughput environments.You will own the end-to-end architecture of real-time voice systems, including speech recognition, LLM orchestration, dialog management, speech synthesis, and low-latency streaming pipelines—designed for reliability, scalability, and cost efficiency.This role is highly hands-on and strategic, bridging research, engineering, and production infrastructure.Key ResponsibilitiesArchitecture & System DesignDesign low-latency, real-time voice agent architectures for local/on-prem deploymentDefine scalable architectures for ASR → LLM → TTS pipelinesOptimize systems for GPU utilization, concurrency, and throughputArchitect fault-tolerant, production-grade voice systems (HA, monitoring, recovery)Voice & Conversational AIDesign and integrate:Automatic Speech Recognition (ASR)Natural Language Understanding / LLMsDialogue management & conversation stateText-to-Speech (TTS)Build streaming voice pipelines with sub-second response timesEnable multi-turn, interruptible, natural conversationsModel & Inference EngineeringDeploy and optimize local LLMs and speech models (quantization, batching, caching)Select and fine-tune open-source models for voice use casesImplement efficient inference using TensorRT, ONNX, CUDA, vLLM, Triton, or similarInfrastructure & ProductionDesign GPU-based inference clusters (bare metal or Kubernetes)Implement autoscaling, load balancing, and GPU schedulingEstablish monitoring, logging, and performance metrics for voice agentsEnsure security, privacy, and data isolation for local deploymentsLeadership & CollaborationSet architectural standards and best practicesMentor ML and platform engineersCollaborate with product, infra, and applied research teamsDrive decisions from prototype → production → scaleRequired QualificationsTechnical Skills7+ years in software / ML systems engineering3+ years designing production AI systemsStrong experience with real-time voice or conversational AI systemsDeep understanding of LLMs, ASR, and TTS pipelinesHands-on experience with GPU inference optimizationStrong Python and/or C++ backgroundExperience with Linux, Docker, KubernetesAI & ML ExpertiseExperience deploying open-source LLMs locallyKnowledge of model optimization:QuantizationBatchingStreaming inferenceFamiliarity with voice models (e.g., Whisper-like ASR, neural TTS)Systems & ScalingExperience with high-QPS, low-latency systemsKnowledge of distributed systems and microservicesUnderstanding of edge or on-prem AI deploymentsPreferred QualificationsExperience building AI voice agents or call automation systemsBackground in speech processing or audio MLExperience with telephony, WebRTC, SIP, or streaming audioFamiliarity with Triton Inference Server / vLLMPrior experience as Tech Lead or Principal EngineerWhat We OfferOpportunity to architect state-of-the-art AI voice systemsWork on real-world, high-scale production deploymentsCompetitive compensation and equity (if applicable)High ownership and technical influenceCollaboration with top-tier AI and infrastructure talent