Senior Lead Software Engineer - Python, AI & LLM
Salary not listed • GLASGOW, LANARKSHIRE, United Kingdom • Full-time
Posted 29d ago
Remote Work Policy
On-site
Employment Type
Full-time
Categories
LLM Engineer
About the job
Build the platforms that make advanced AI practical at scale. In this role, you’ll shape standards, tooling, and reliable inference foundations that help engineering teams move faster with confidence. You’ll work hands-on with modern large language model serving stacks and performance tuning, while partnering closely with platform and product stakeholders. As a Senior Lead Software Engineer, you will lead the design and delivery of secure, stable, and scalable platform capabilities that simplify adoption and day-to-day use. You will set technical direction for tooling and runtime foundations, with a focus on production-grade large language model inference and Kubernetes-based deployment patterns. You will partner across engineering teams to improve reliability, developer experience, and operational outcomes through automation and standards. You will mentor engineers and reinforce inclusive, high-accountability ways of working.
Responsibilities
- Lead the design and delivery of platform standards and tooling (CLIs, SDKs, libraries, templates, automated checks) to simplify adoption.
- Engineer and operate production large language model inference services using modern serving engines (e.g., vLLM, TensorRT-LLM, SGLang).
- Drive Kubernetes-based deployment patterns, scaling strategies, networking, and troubleshooting for reliable platform operations.
- Optimize inference performance by understanding GPU memory behavior, key-value cache sizing, and memory bandwidth/compute trade-offs.
- Evaluate and apply inference-time quantization approaches to balance latency, throughput, cost, and quality.
- Implement secure, high-quality production code and automation for resiliency, observability, and operational readiness.
- Establish and maintain architecture and design artifacts, enforcing constraints and non-functional requirements.
- Drive team adoption of AI-assisted engineering practices to improve code quality, delivery speed, and operational outcomes.
- Apply knowledge of SDLC toolchain, including AI-assisted development and automation capabilities, to enhance automation value.
Requirements
- Hands-on experience building standards and tooling (CLIs, SDKs, libraries, templates, automated checks) for platform adoption.
- Deep, hands-on experience with large language model inference systems (e.g., vLLM, TensorRT-LLM, SGLang).
- Hands-on experience building and operating production services on public cloud platforms (e.g., AWS).
- Ability to design, deploy, and troubleshoot cloud infrastructure components (compute, storage, networking, IAM) in AWS.
- Demonstrated Kubernetes expertise in deployments, scaling, networking, and troubleshooting.
- Working knowledge of GPU memory architecture, including key-value cache sizing and performance trade-offs.
- Understanding of inference-time quantization trade-offs and their impact on serving behavior.
- Ability to produce architecture and design artifacts and translate them into secure, scalable implementations.
- Strong understanding of SDLC practices, including CI/CD, resiliency, and security.
- Hands-on experience using enterprise-authorized AI-assisted software development tools and critically evaluating their outputs.
- Understanding of responsible AI use in engineering workflows, including data sensitivity and secure handling of inputs/outputs.