AI Inference Engineer

IC Resources

Greater London

On-site

GBP 80,000 - 120,000

Full time

14 days+

Get a reply from this recruiter

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

Intellectual Capital Resources Ltd in London seeks a Research Scientist/Research Engineer focused on accelerating inference for brain-inspired AI.

You will profile costs, implement quantisation, sparsity, pruning, and distillation, and optimize KV caching, decoding, batching, and attention for various backends.

You’ll work with CUDA/Triton, vLLM/TensorRT-LLM and llama.cpp on GPU/CPU accelerators, and contribute to rigorous experiments and potential publications.

Qualifications

  • Bachelor’s/Master’s/PhD in a quantitative field as listed.
  • Strong understanding of modern DL and LLM architectures and their run costs.
  • Strong Python and PyTorch/JAX experience with hands-on profiling on GPUs/CPUs.
  • Foundations in linear algebra, probability, optimisation, numerical methods or information theory.
  • Rigorous experimental mindset spanning theory, experiment and implementation.
  • Publications or open-source contributions valued; industry experience not essential.

Responsibilities

  • Perform inference profiling and cost modelling (compute, memory, latency, energy).
  • Develop efficient inference methods: quantisation, sparsity, pruning, distillation, compression.
  • Optimize inference: KV cache management, speculative decoding, batching, efficient attention.
  • Engage in GPU programming and performance engineering (CUDA, kernels, profiling).
  • Explore non-Transformer and brain-inspired architectures and HW-aware ML.
  • Collaborate across research and engineering teams to advance core tech.

Skills

Python
PyTorch
JAX
CUDA
Triton
Profiling
Optimization
Deep learning
LLM architectures
Optimization theory

Education

Bachelor’s, Master’s or PhD in Maths, CS, Physics, Engineering, Neuroscience or related quantitative field

Tools

vLLM
TensorRT-LLM
llama.cpp
CUDA tooling / Profiling tools

Job description

Our client, an early-stage AI research lab developing brain-inspired approaches to more efficient AI, is hiring a Research Scientist / Research Engineer focused on inference, making models faster, smaller and more energy efficient, with direct influence on the company’s core technology.

Focus areas (one or more):
  • Inference profiling and cost modelling (compute, memory capacity and bandwidth, cache growth, latency, throughput, energy)
  • Efficient inference methods (quantisation, sparsity, pruning, distillation, compression, low-precision computation)
  • Inference optimisation (KV cache management, speculative decoding, batching, efficient attention, vLLM/TensorRT-LLM/SGLang/llama.cpp)
  • GPU programming and performance engineering (CUDA, Triton, custom kernels, profiling)
  • Non-Transformer and brain-inspired architectures (state-space, recurrent, associative-memory, long-context, spiking and neuromorphic models)
  • Hardware-aware ML (roofline analysis, on-device and edge inference, energy modelling)
Requirements:
  • Bachelor’s, Master’s or PhD in Maths, CS, Physics, Engineering, Neuroscience or a closely related quantitative field
  • Strong understanding of modern deep learning and LLM architectures, and of what makes them expensive to run (attention, KV caching, autoregressive decoding)
  • Strong Python and PyTorch/JAX experience, with hands-on experience profiling and optimising model performance on GPUs, accelerators or CPUs
  • Strong foundations in several of: linear algebra, probability, optimisation, numerical methods, information theory, dynamical systems or statistical learning
  • Rigorous experimental mindset, with the ability to move between mathematical reasoning, experimentation and implementation
  • Research publications, open-source contributions or substantial independent projects valued (industry experience not essential)

Location: London. Full-time, permanent.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

AI Research Engineer
AI Research Engineer

IC Resources • Greater London

On-site
GBP 65,000 - 120,000
Ai Software Engineer
Ai Software Engineer

IC Resources • Greater London

On-site
GBP 70,000 - 120,000
AI Inference Engineer — Brain-Inspired, Efficient Models
AI Inference Engineer — Brain-Inspired, Efficient Models

IC Resources • Greater London

On-site
GBP 80,000 - 120,000
AI Software Engineer
AI Software Engineer

IC Resources • Greater London

On-site
GBP 80,000 - 140,000
Research Scientist (LLM Architectures)
Research Scientist (LLM Architectures)

CommonAI C.I.C. • Cambridge

On-site
GBP 90,000 - 130,000
Top-tier Claude Code subscription
Cambridge office near train station
Competitive salary package and pension
+1
Research Scientist (LLM Architectures)
Research Scientist (LLM Architectures)

CommonAI Holdings Ltd • Cambridge

Hybrid
GBP 70,000 - 110,000
Collaborative environment
High impact work
Salary and pension
+3
Research Scientist (Llm Architectures)
Research Scientist (Llm Architectures)

Commonai C.I.C. • Cambourne

On-site
GBP 65,000 - 90,000
Competitive salary package
Pension
Professional development
+2
GPU Kernel and Performance Engineer
GPU Kernel and Performance Engineer

CommonAI C.I.C. • Cambridge

On-site
GBP 120,000 - 170,000
Competitive salary
Pension
Professional development
+1
GPU Kernel and Performance Engineer
GPU Kernel and Performance Engineer

CommonAI Holdings Ltd • Cambridge

Hybrid
GBP 90,000 - 120,000
Competitive salary
Pension
Professional development
+2
Member of Technical Staff
Member of Technical Staff

develop • Greater London

On-site
GBP 120,000 - 180,000
Competitive salary
Meaningful equity
Visa sponsorship
+2