At a Glance
- Tasks: Join our team to build and optimise AI inference engines for cutting-edge models.
- Company: Dynamic tech company focused on innovative AI solutions.
- Benefits: Competitive salary, equity options, remote work, and growth opportunities.
- Other info: Fast-paced environment with opportunities for self-directed learning and career advancement.
- Why this job: Make a real impact in AI while working with the latest technologies.
- Qualifications: 3+ years in software engineering with expertise in ML inference and GPU programming.
The predicted salary is between 60000 - 80000 £ per year.
We are looking for an AI Inference Engineer to join our growing team. We build and run the inference engine behind every Perplexity query and deploy dozens of model architectures at scale with tight latency and cost budgets. Our stack is Rust, Python, CUDA, and CuTe DSL.
Responsibilities
- New models support. Support transformer-based retrieval, text-generation, and multimodal models in our inference infrastructure, from weight loading, request scheduling and KV-cache management to support in API Gateway.
- GPU kernels migration to CuTe DSL. Port our in-house CUDA kernels to NVIDIA's CuTe DSL so they run on GB200 today and are portable to Vera Rubin racks tomorrow.
- Rust-native serving runtime. Develop our internal Rust-based inference server to solve all Python pains and keep up with rapidly growing traffic.
- Performance optimisation. Profile and fix bottlenecks from network ingress through continuous batching and GPU kernels interleaving.
- Reliability and observability. Build dashboards, alerts, and automated remediation so we catch regressions before users do. Respond to and learn from production incidents.
Who We’re Looking For
- Deep experience with GPU programming and performance work (CUDA, Triton, CUTLASS, or similar). Any other deep systems programming experience is a plus.
- You understand modern LLM architectures and are able to bring them up reliably in a production environment.
- You've built and operated production distributed systems under real load - ideally performance-critical ones.
- Comfortable working across languages and layers: Rust for the serving runtime, Python for model code, CUDA/CuteDSL for kernels.
- You own problems end-to-end. You can read a research paper on Monday, write a kernel on Wednesday, and debug a production incident on Friday.
- Self-directed. You do well in fast-moving environments where the path forward isn't laid out for you.
Nice-to-have
- ML compilers and framework internals: PyTorch internals, torch.compile, custom operators.
- Distributed GPU communication: NCCL, NVLink, InfiniBand, RDMA libraries, model/tensor parallelism.
- Low-precision inference: INT8/FP8/FP4 quantization, mixed-precision serving.
- Profiling and debugging tools: Nsight Compute/Systems, CUDA-GDB, PTX/SASS analysis.
- Container orchestration: Kubernetes, GPU scheduling, autoscaling inference workloads.
Qualifications
- 3+ years of professional software engineering experience with meaningful work on ML inference or high-performance systems.
- Familiarity with at least one deep learning framework (PyTorch, JAX, TensorFlow).
- Understanding of GPU architectures (memory hierarchy, warp scheduling, tensor cores).
- Understanding of common LLM architectures and inference optimization techniques (e.g. quantization, speculative decoding, prefill-decode disaggregation).
Final offer amounts are determined by multiple factors including experience and expertise. Equity: In addition to the base salary, equity may be part of the total compensation package.
Member of Technical Staff (AI Inference Engineer) employer: Perplexity
Join our innovative team as an AI Inference Engineer, where you'll be at the forefront of cutting-edge technology in a dynamic and collaborative work environment. We offer competitive salaries, equity options, and a culture that fosters continuous learning and professional growth, all while working in a location that encourages creativity and innovation. With a focus on performance optimisation and reliability, you'll have the opportunity to make a significant impact on our products and contribute to the future of AI.
StudySmarter Expert Advice🤫
We think this is how you could land Member of Technical Staff (AI Inference Engineer)
✨Tip Number 1
Network, network, network! Reach out to folks in the industry, especially those who work with AI and GPU programming. Join relevant online communities or attend meetups to make connections that could lead to job opportunities.
✨Tip Number 2
Show off your skills! Create a portfolio showcasing your projects, especially those involving CUDA, Rust, or any deep learning frameworks. This will give potential employers a taste of what you can do and set you apart from the crowd.
✨Tip Number 3
Prepare for technical interviews by brushing up on your knowledge of modern LLM architectures and performance optimisation techniques. Practice coding challenges related to GPU programming and distributed systems to demonstrate your expertise.
✨Tip Number 4
Don’t forget to apply through our website! We’re always on the lookout for talented individuals like you. Tailor your application to highlight your experience with AI inference and high-performance systems to catch our eye.
We think you need these skills to ace Member of Technical Staff (AI Inference Engineer)
Some tips for your application 🫡
Tailor Your CV:Make sure your CV highlights your experience with GPU programming and performance work. We want to see how your skills align with our tech stack, so don’t be shy about showcasing your Rust, Python, and CUDA expertise!
Craft a Compelling Cover Letter:Your cover letter is your chance to shine! Tell us why you’re excited about the role and how your background in ML inference or high-performance systems makes you a perfect fit for our team. Keep it engaging and personal!
Showcase Your Projects:If you've worked on any relevant projects, especially those involving distributed systems or modern LLM architectures, make sure to mention them. We love seeing real-world applications of your skills, so include links or descriptions!
Apply Through Our Website:We encourage you to apply directly through our website. It’s the best way for us to receive your application and ensures you’re considered for the role. Plus, it’s super easy – just follow the prompts!
How to prepare for a job interview at Perplexity
✨Know Your Tech Stack
Make sure you’re well-versed in Rust, Python, CUDA, and CuTe DSL. Brush up on how these technologies interact, especially in the context of AI inference. Being able to discuss your experience with these languages and frameworks will show that you’re ready to hit the ground running.
✨Demonstrate Problem-Solving Skills
Prepare to discuss specific challenges you've faced in previous roles, particularly around GPU programming and performance optimisation. Use the STAR method (Situation, Task, Action, Result) to structure your answers, showcasing how you’ve tackled complex problems in production environments.
✨Familiarise Yourself with LLM Architectures
Since the role involves working with modern LLM architectures, make sure you can explain how they function and how you’ve implemented them in the past. Be ready to discuss inference optimisation techniques like quantization and speculative decoding, as this will demonstrate your depth of knowledge.
✨Show Your Self-Directed Nature
This position requires someone who thrives in fast-paced environments. Prepare examples that highlight your ability to work independently and navigate ambiguity. Discuss times when you took initiative to solve problems or improve processes without being directed.
