Datatech Analytics
Machine Learning Engineer — Inference & Performance
How your CV stacks up
Upload your CV to see how well it fits this job role
?%
Global Financial Services Institution | Mid–Senior | Location London
Make machine learning models faster.
Building a model is one thing. Making it fast, efficient and reliable in production is another.
Our client is looking for a Machine Learning Engineer focused on inference optimisation and performance. You’ll work on ML solutions across risk, payments and client products, where low latency and efficiency are critical.
Much of the work is CPU-based, low batch and latency sensitive, with models running in a regulated environment.
What you’ll do
You’ll take production models and improve their performance by:
- Profiling models and identifying bottlenecks
- Reducing inference latency and improving throughput
- Applying quantisation while maintaining model accuracy
- Optimising computation graphs and threading
- Benchmarking changes against a clear baseline
- Deploying and monitoring optimised models
- Identifying the next performance improvement
Reasons to use Rodeo
Start with a chat, not a search bar
Grad scheme, placement, apprenticeship? Not sure what you want yet — that's fine. Your agent talks it through with you and turns "I have no idea" into a shortlist.
It searches the market for you
Every day your agent scans the market matching roles against what actually matters to you, not just keywords on a CV.
Only hits
No noise. No "maybe this fits." Just roles with a clear explanation of why they're right — and where to focus when applying.
We want engineers who can clearly explain: what was the problem, what did you change, and what measurable difference did it make?
What you’ll need
- Strong Python plus C++, Rust, Go or Java
- Proven experience optimising ML inference in production
- Practical experience with quantisation
- Experience with at least two of: ONNX Runtime, OpenVINO, oneDNN, IPEX, TVM, TensorRT, vLLM or llama.cpp
- PyTorch or TensorFlow
- XGBoost or LightGBM
- Docker, Kubernetes and CI/CD
- A strong performance-engineering mindset and a disciplined approach to benchmarking
Useful experience
- CPU optimisation: AVX-512, VNNI, AMX or NUMA
- Financial services
- Real-time or streaming inference
- Kernel-level optimisation
- Open-source ML tooling
Senior level
For Senior Engineers, we want to hear about a specific optimisation you led, including the baseline, what you changed and the measurable result.
Get help with your application
Your very own career expert that helps elevate your application to the next level.
GPU background? Absolutely still relevant. If you understand why your CUDA/GPU optimisation delivered better performance, the inference toolchain can be learned.
What this isn't
This isn't a research role, distributed GPU training role or pure ML platform position.
The focus is simple: make production ML models faster, more efficient and more reliable.
You’ll also work within a regulated environment, so experience with model documentation, validation and monitoring is important.
If performance engineering and production ML are your strengths, this is an opportunity to work on systems where the improvements you make have a measurable impact.
Contact
For a confidential call, contact justin.toomey@datatech.org.uk.
“It took my CV and asked me questions relevant to understanding what kind of jobs to suggest for me. Suggestions were almost perfect. Jobs were exactly what I’ve been looking for.”
Jessica, London
Skills
Location