Senior Lead Software Engineer - Python, AI & LLM

Overview

As Senior Lead Software Engineer, you will architect and deliver secure, scalable platform capabilities for enterprise AI use, focusing on production-grade LLM inference and Kubernetes-based deployments. You’ll set tooling standards, improve reliability and developer experience, and partner with cross-functional teams to automate and raise operational excellence. You will mentor engineers and foster inclusive, high-accountability practices, driving meaningful impact in a corporate AI platform. This role offers the opportunity to shape scalable, secure AI infrastructure used by multiple teams.

Responsibilities

• Lead design and delivery of platform standards and tooling (CLI, SDKs, libraries, templates, automated checks) to simplify adoption
• Operate production LLM inference services using modern serving engines (vLLM, TensorRT-LLM, SGLang, LLM-D or equivalents)
• Define Kubernetes-based deployment patterns, scaling, networking, and troubleshooting for reliable platform operations
• Optimize inference performance via GPU memory behavior, cache sizing, and compute bottlenecks
• Assess inference-time quantization trade-offs for latency, throughput, cost, and output quality
• Implement secure, production-grade code and automation to strengthen resiliency, observability, and operational readiness
• Create and maintain architecture/design artifacts enforcing non-functional requirements through implementation and automation
• Drive adoption of enterprise AI-assisted engineering practices (code review, testing, incident analysis) with consistent validation standards
• Leverage SDLC tools and AI-assisted development/automation to enhance automation value

Key requirements

• Hands-on experience building platform tooling (CLI, SDKs, libraries, templates, automated checks)
• Deep experience with LLM inference systems (vLLM, TensorRT-LLM, SGLang, LLM-D)
• Production services on AWS
• Design, deployment, and troubleshooting of AWS-based cloud infrastructure for platform services
• Kubernetes expertise across deployments, scaling, networking, and troubleshooting
• Knowledge of GPU memory architecture, cache sizing, and memory bandwidth vs compute trade-offs
• Understanding of inference-time quantization and its impact on latency/throughput
• Ability to translate architecture into secure, scalable implementations
• Strong SDLC, CI/CD, resiliency, and security practices
• Experience with AI-assisted software development tools and evaluating AI outputs for correctness, performance, and security
• Understanding of responsible AI use in engineering workflows
• collaboration
• mentorship
• ownership
• vLLM
• TensorRT-LLM
• SGLang

Report this job