AI Systems Engineer

As an AI Systems Engineer at Shunya Labs, you will play a crucial role in optimizing AI models, designing infrastructure, and conducting research. You will be responsible for evaluating, hosting, and optimizing a variety of AI models including ASR, LLMs, and multimodal systems. Your key responsibilities will include: - **AI Model Evaluation & Optimization** - Evaluate, benchmark, and optimize AI models for latency, throughput, and accuracy. - Implement advanced inference optimizations using ONNX Runtime, TensorRT, quantization, and GPU batching. - Continuously research and experiment with the latest AI runtimes, serving frameworks, and model architectures. - Develop efficient caching and model loading strategies for multi-tenant serving. - **AI Infrastructure & Orchestration** - Design and develop a central orchestration layer to manage multi-model inference, load balancing, and intelligent routing. - Build scalable, fault-tolerant deployments using AWS ECS/EKS, Lambda, and Terraform. - Use Kubernetes autoscaling and GPU node optimization to minimize latency under dynamic load. - Implement observability and monitoring (Prometheus, Grafana, CloudWatch) across the model-serving ecosystem. - **DevOps, CI/CD & Automation** - Build and maintain CI/CD pipelines for model integration, updates, and deployment. - Manage Dockerized environments, version control, and GPU-enabled build pipelines. - Ensure reproducibility and resilience through infrastructure-as-code and automated testing. - **Frontend & Developer Tools** - Create React/Next.js-based dashboards for performance visualization, latency tracking, and configuration control. - Build intuitive internal tools for model comparison, experiment management, and deployment control. - Utilize Cursor, VS Code, and other AI-powered development tools to accelerate iteration. - **Client Interaction & Solutioning** - Work closely with clients and internal stakeholders to gather functional and performance requirements. - Translate abstract business needs into deployable AI systems with measurable KPIs. - Prototype quickly, iterate with feedback, and deliver robust production systems. - **Research & Continuous Innovation** - Stay updated on the latest AI research and model releases. - Evaluate emerging frameworks for model serving, fine-tuning, and retrieval. - Implement performance or cost improvements in the model serving stack and contribute to the internal AI knowledge base. In terms of qualifications, you should have strong proficiency in Python, TypeScript/JavaScript, Bash, and modern software development practices. Deep understanding of Docker, Kubernetes, Terraform, and AWS is required. Experience with inference optimization, CI/CD pipelines, and React/Next.js is essential. Additionally, soft skills like problem-solving in ambiguous environments, research abilities, and strong communication skills are highly valued. Shunya Labs is at the forefront of building Voice AI Infrastructure for Enterprises, focusing on speech intelligence and domain-specific voice applications. If you are passionate about AI, infrastructure engineering, and research, this role offers a unique opportunity to make a significant impact in the field.,