Senior Lead Software Engineer - Inference Platform
Core
Architecting and deploying secure, scalable cloud platforms optimized for AI and ML workloads, specifically high-performance LLM inference.
Role type
Senior Lead Software Engineer (Inference Platform)
Builds
Secure, scalable cloud platforms and high-performance LLM inference serving infrastructure.
Domain
Financial Services / Cloud Infrastructure / Machine Learning
Deliverable
production ML models | infrastructure
Required skills
System design, Kubernetes, containerization (Docker), Python/Go/Java/C#, Cloud delivery models (IaaS/PaaS/SaaS), Infrastructure as Code, AI-assisted development governance, Responsible AI workflows, Microservices architecture, CI/CD pipelines, Observability (Prometheus/Grafana), MLOps.
Preferred skills
NVIDIA GPU infrastructure software (DCGM, BCM, Dynamo Inference), vLLM optimization, Low-latency high-throughput model serving.
Responsibilities
Provide technical direction aligned with business goals; Develop secure, high-quality production code; Review, debug, and improve code written by others; Influence product design and technical operations; Champion firmwide SDLC frameworks and best practices; Architect and deploy secure, scalable cloud platforms for AI/ML; Partner with AI teams to translate compute requirements into infrastructure needs; Monitor, manage, and optimize cloud resources for performance and cost; Build CI/CD pipelines and automation; Drive adoption of AI-assisted engineering practices; Establish measurable validation standards for secure coding and testing.
Seniority
Senior, hands-on IC with leadership responsibilities
