Staff Applied AI Inference Engineer

Crusoe Energy Systems; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Benefits offered by this job

Health benefits

401(k) match

Paid time off

Mental wellness support

Job summary

Crusoe Energy Systems in San Francisco is hiring an ML systems engineer focused on making large language models run faster, cheaper, and more reliably in production. You will own the end-to-end inference stack, profiling time and cost, and bringing modern optimization techniques to real deployments.

The role involves hands-on coding, low-level optimization, and collaboration with customer engineering teams to tailor deployments to their workloads and latency targets.

Qualifications

• Proven experience shipping production-grade ML inference systems.
• Strong background in optimizing LLMs for latency and throughput.
• Experience profiling kernels and serving stacks for performance.
• Comfort with customer-facing discussions and requirements.

Responsibilities

• Own end-to-end optimization of inference stacks for evolving models.
• Profile, tune, and debug performance across GPUs and kernels.
• Collaborate with customers to tailor deployments and monitor results.
• Lead experiments from concept to production with measurable gains.

Skills

Production code

LLM optimization

Performance profiling

Customer-facing

Python

Communication skills

AI/ML pipelines

Education

Bachelor/Master/PhD in CS or related

Tools

CUDA

Docker

Kubernetes

vLLM

SGLang

Job description

• You will spend your time making large language models run faster, cheaper, and more reliably in production


• That means owning the inference stack end to end: profiling where time and cost go, bringing modern optimization techniques into real deployments, and getting deep into the serving code when the defaults are not good enough


• This is core systems and performance work on some of the most demanding models in use today


• The work is applied, not academic


• The optimizations you build land in real customer deployments, each with its own models, traffic patterns, latency targets, and cost constraints


• So while performance is the heart of the role, you will also work directly with customer engineering teams to tailor deployments to their needs, take a workload from an early proof of concept to a fully monitored production service, and make sure the gains you engineer actually show up for the people running the workload


• To set expectations clearly, this is a hands-on engineering role built around coding, profiling, and low-level optimization


• It also carries a customer-facing side, along with elements of product and technical solutions work, because that is where the performance work gets proven


• Bring current inference techniques into production and refine them


• Design and optimize serving architectures, including prefill and decode disaggregation, request routing, and related approaches


• Work down into the serving stack, from frameworks like vLLM and SGLang to the CUDA kernels underneath, profiling and running in-depth analysis to find and fix performance problems


• Adapt and scale optimization methods across many kinds of ML models, with an emphasis on large language models


• Profile and tune deployments against clear targets for latency, throughput, and cost, and keep them dependable under real traffic


• Tailor deployments to each customer’s models and constraints, partnering with their engineering teams to move a workload from an early proof of concept through to a live, well-monitored production service


• Build and support the software and product features around the inference stack in a production setting, using one or more general-purpose languages, with Python preferred given how central it is to ML work


• Experiment quickly: take fuzzy goals, shape them into clear specs and focused proofs of concept, run fast experiments to find what works, and ship well-tested results without delay


• Own delivery end to end, from the first experiment through to the optimization running in production, keeping the underlying performance goals, clear specs, and follow-through front of mind, and drafting features and product requirement documents together with other engineering and product teams


• Work through ambiguity and make sound calls on tradeoffs and tooling, steering away from complexity that is not needed


• Take real pride and ownership in your work, hold yourself accountable, and look for the same from the people around you

Benefits

• Health & wellbeing: Comprehensive health benefits designed to support your overall wellness


• Time away: Paid time off for vacations, family bonding, and unexpected needs


• 401(k) match: Build your financial future with our 401(k) matching program


• Mental wellness: Resources and support for your emotional wellbeing and navigating life’s challenges

• Hands-on experience shipping code in production with one or more general-purpose languages, such as Python or C++, with a strong preference for Python


• Familiarity with methods for optimizing LLMs for high throughput / low latency inference


• Comfort with modern LLM serving frameworks such as vLLM or SGLang, and with profiling and analyzing performance down to the kernel level


• A firm grasp of how GPUs are built and how they behave


• Strong communication skills, particularly when explaining hard technical topics to customers and teammates


• A working knowledge of AI/ML pipelines and the full path of developing and deploying ML models


• Clear interest and hands‑on experience with large language models


• A Bachelor’s, Master’s, or Ph.D. in Computer Science, Engineering, Mathematics, or a related field


• A track record of making software systems run faster, especially for large language models


• Experience with CUDA or comparable technologies


• A strong command of software engineering fundamentals, with a record of building and shipping AI/ML inference systems


• Experience with Docker and Kubernetes


• Prior work building or tuning AI/ML projects, particularly in a customer-facing setting