Senior Lead Software Engineer – Python, AI & LLM

Overview

In this Senior Lead role, you shape secure, scalable platform capabilities for enterprise AI and data platforms. You will set tooling and runtime standards, focusing on production-grade LLM inference and Kubernetes deployment patterns. You’ll partner with engineering teams to improve reliability, developer experience, and operational readiness, while mentoring others. This is a hands-on, impact-focused position that blends deep systems work with cross-team collaboration and governance. You’ll contribute to a mission of enabling safe, scalable AI at scale across the organization.

Responsibilities

• Design and deliver platform standards and tooling to ease adoption (CLI, SDKs, libraries, templates, automated checks)
• Build and operate production LLM inference services using modern serving engines
• Drive Kubernetes-based deployment patterns, scaling, networking, and troubleshooting for reliable platform ops
• Optimize inference performance with GPU memory considerations and bottleneck analysis
• Assess inference-time quantization trade-offs for real-world workloads
• Develop secure, high-quality production code and automation for resiliency and observability
• Maintain architecture/design artifacts and enforce non-functional requirements through automation
• Promote enterprise AI-assisted engineering practices to improve quality, speed, and operational outcomes
• Leverage SDLC tools and enterprise AI-assisted development to enhance automation and value

Key requirements

• Hands-on experience building standards and tooling to improve platform adoption
• Deep, hands-on experience with LLM inference systems (e.g., vLLM, TensorRT-LLM, SGLang, LLM-D)
• Hands-on experience operating production services on AWS
• Ability to design, deploy, and troubleshoot AWS cloud infrastructure components for platform services
• Demonstrated Kubernetes expertise across deployments, scaling, networking, and troubleshooting
• Knowledge of GPU memory architecture, including key-value cache sizing and performance trade-offs
• Understanding of inference-time quantization and its impact on latency and throughput
• Ability to translate architecture into secure, scalable implementations
• Strong SDLC, CI/CD, resiliency, and security practice understanding
• Experience with enterprise AI-assisted software development tools and evaluating AI outputs for correctness, performance, and security
• Understanding of responsible AI use, data sensitivity, secure inputs/outputs, and resiliency/security expectations

• collaborative and cross-functional teamwork
• mentorship and coaching
• problem-solving mindset with focus on reliability and developer experience
• vLLM
• TensorRT-LLM
• SGLang

…