Description :
We're looking for a Senior Platform Engineer to architect and build the robust infrastructure that powers our next-generation Voice AI platform. In this role, you'll design and implement systems that handle massive scale, ensure ultra-low latency, and deliver exceptional reliability. This is a high-impact role where your work will form the technical backbone of real-time AI conversations used by some of India's leading :
- End-to-end ownership : Drive product development from requirements gathering to architecture, implementation, deployment, and post-launch support.
- Scale massively : Design and build infrastructure capable of supporting hundreds of thousands of concurrent AI conversations daily.
- Innovate constantly : Stay on top of the latest research and technology to implement cutting-edge infrastructure solutions.
- Architect for growth : Design highly scalable, distributed systems that adapt to evolving business needs and product features.
- Optimise relentlessly : Identify and eliminate system bottlenecks to deliver low-latency, high-throughput performance for real-time voice AI.
Requirements : Core Experience :
5+ years of experience in backend / platform / infrastructure engineering.Proven track record building and scaling distributed systems in production environments.Deep knowledge of Kubernetes (EKS / GKE) - including custom operators, CRDs, and cluster operations.Proficiency in AWS (preferred) or GCP, using Infrastructure-as-Code tools (Terraform, CloudFormation).Strong experience with monitoring and observability stacks (Prometheus, Grafana, ELK).Proficient in Python (especially with FastAPI, asyncio) and / or Go.Systems and Performance :
Experience with high-throughput, low-latency systems (ideally in real-time domains).Deep understanding of systems design, caching (Redis), and messaging queues (Kinesis, SQS).Strong expertise with PostgreSQL and Redis.Knowledge of networking, service mesh, and security best practices in cloud environments.Bonus Skills (Nice to Have) :
Experience deploying and monitoring machine learning models in production.Familiarity with GPU orchestration (NVIDIA, CUDA) and real-time inference optimization.Knowledge of PyTorch, TensorFlow, or similar ML frameworks.Familiarity with WebRTC, real-time audio processing, or streaming architecture optimisations.Experience with multi-tenant SaaS platforms.(ref : hirist.tech)