Tailored answers, filled into supported job forms.Your tailored resume and answers, filled into supported job forms for you to review.

Download the Chrome Extension
AI AdoptionJob SimulationCertificationsRoadmapsPricing
Sign In
OneRoadmap

OneRoadmap is a career platform built around ORI, its AI career agent. ORI finds overlooked job opportunities, matches them to your profile and shows the skill gaps to close, with roadmaps, challenges, job simulations and certifications to close them. When you are ready, it prepares a tailored resume, application answers and an application strategy, with a cover letter where the application asks for one. The OneRoadmap Chrome extension fills supported application forms for you to review and submit, and you keep track of every application in one place.

gaurav.ghai@oneroadmap.io
Delhi NCR, India

Platform

  • AI Roadmaps
  • Free Certifications
  • Learning Resources
  • Pricing

Training

  • AI Adoption Workshops
  • Expert Sessions
  • Upcoming Events
  • Workshop Gallery

Company

  • About
  • Blog
  • Contact

Legal

  • Privacy
  • Terms
  • Refunds
  • Delete your data

© 2026 OneRoadmap

Operated by Ghai Technologies, India · International operations through One Roadmap Marketing Management, Dubai, UAE

Built for your next chapter.

Open roles

SOFTWARE · Compute & Infrastructure

Hardware-Aware Model Optimisation - Member of Technical Staff

Callosum

SeniorOn-site · LondonFullTimeListed 6d ago
Apply now

SEED · 3mo ago

$100M

HQ

🇬🇧 London

Open roles

14

How to stand out for Hardware-Aware Model Optimisation - Member of Technical Staff at Callosum

Auto Match agent

Let ORI find you the best jobs.

Set up your Auto Match agent once - your target role, level and where you want to work. It searches every day, scores each opening against your profile and resume, and delivers the ones worth applying to, with a prepared application a click away.

Searches every day Scored against your profile Applications prepared for you
Sign in & set up Auto Match agent

Resume & career call

Get your resume reviewed for this role - 30-minute 1:1 call

Line-by-line resume feedback for this application, how to position your Role Readiness, and a clear plan for what to do next - with a OneRoadmap career coach.

Experience Senior · 6+ yrs

About the role

from listing

About Us

We’re living through a Cambrian explosion of intelligence: new models and new chips, each specialised for different tasks, are arriving all at once. The result is a new era for AI, one of radical heterogeneity.

Callosum is the Intelligent Systems Company. We believe the next generation of AI won't be defined by any single model or chip, but by intelligent systems in which hardware and intelligence co-evolve. We are building the infrastructure that unifies heterogeneous compute across the full stack. This opens a new axis of scaling intelligence: a dynamic system that tailors itself to what each workload actually needs, whether that's speed, cost, precision, or whatever unit comes next.

The last era scaled on a different bet: one bigger model, more of the same chip, more data. That bet is running into structural limits. Frontier models offer extraordinary capability at unsustainable cost, one that today's monolithic infrastructure was never designed to serve.

Our founding principle is that intelligence comes from many specialised systems working together, not from any single component. We build the software orchestration layer that co-evolves models, workflows and silicon into one system, delivering inference tailored to every workload, and demonstrating orders-of-magnitude leaps in capability and cost.

Because our software spans the full stack, our engineering team works directly with heterogeneous accelerators and frontier silicon, including Cerebras, d-Matrix, Intel, NVIDIA, AMD, Normal Computing, Tenstorrent, GreatSky, and Mixx. We are not stopping at today's chips: each new generation of silicon unlocks algorithms that couldn't run before, and we intend to be first to them, every time. If we get it right, it will belong to everyone building on it - not to any single vendor.

In our latest funding round, we raised $100M, led by Atomico with participation from Plural, DCVC and the UK Sovereign AI Fund’s first investment. With this, we are building the infrastructure for the next era of intelligence.

We are engineers and scientists based in London, working across the full depth of the stack. We are curious, intellectually honest, and building what doesn't exist yet. If you thrive on uncharted territory and are energised by the scale of the challenge, we'd love to hear from you.

ABOUT THE ROLE

Callosum believes that the next generation of AI systems will emerge from models and hardware being optimised together. Today's model architectures have largely evolved around the capabilities of conventional GPUs, leaving significant opportunities unexplored as new accelerator architectures emerge. We are building infrastructure that allows models to be adapted to different computational substrates, rather than treating them as fixed algorithms that hardware must accommodate.

This role explores how model architectures and inference algorithms can be adapted to exploit heterogeneous hardware, creating specialised variants with different trade-offs between capability, latency, and cost. You will investigate transformations spanning numerics, sparsity, model structure, memory, and execution, alongside new algorithms designed around emerging accelerators. A central part of the work is developing automated approaches to these adaptations and rigorous evaluations that establish when the resulting models offer meaningful advantages.

WHAT YOU'LL BUILD

  • Develop hardware-aware transformations that adapt models to different accelerator architectures and execution environments.
  • Explore numerical, structural, and memory-related optimisations to create model variants with different capability, latency, and cost trade-offs.
  • Investigate new inference algorithms, including speculative decoding, designed to exploit heterogeneous computational resources.
  • Develop automated methods for discovering, characterising, and optimising hardware-specialised model variants.
  • Build evaluation methods that measure model quality and establish the trade-offs introduced by hardware-aware adaptations.

WHAT SETS YOU APART

  • Deep understanding of modern LLM architectures, including attention mechanisms, model structure, and their implications for inference.
  • Experience in model architecture research, efficient inference, or hardware-aware machine learning.
  • Familiarity with a range of architectures, such as mixture-of-experts, diffusion, JEPA, or alternative attention mechanisms.
  • Strong intuition for the interactions between model capability, numerical behaviour, memory requirements, and execution efficiency.
  • Experience designing rigorous experiments to assess model quality, efficiency, and the effects of architectural modifications.

What We Offer

  • Competitive Salary, determined by skills and experience
  • Equity & Ownership
  • Private healthcare
  • We offer Visa sponsorship and relocation benefits to hire the best in the world
  • We work in person at our London office. You'll have the tools, space and setup to do your best work, and if you have specific needs, just tell us

We're committed to building an inclusive workplace where everyone feels welcome, and believe in equal opportunities for all.

Apply on company site

Meet Ori - your career agent on WhatsApp

Find jobs, get your roadmap, check if you're ready for a role and prepare applications - in chat, any language.

Ask Ori about this role
Checking your fit…
Callosum

AI Software Infrastructure

Building software infrastructure allowing AI workloads to run across different chips and models

Company pageWebsite

More at Callosum

CallosumCompute & InfrastructureFunded

On-site · London

Senior · 6d ago

Systems Simulation & Performance Modelling - Member of Technical Staff
View role
CallosumOffice of the CTOFunded

On-site · London

Senior · 5+ yrs · 3mo ago

Security Lead - Member of Technical Staff
View role
CallosumGeneral CapabilitiesFunded

On-site · London

Senior · 5+ yrs · £101K – £192K • Offers Equity · 3mo ago

Research Engineer, Evals - Member of Technical Staff
LLMsAgentic Systems+6 more
View role
CallosumGeneral CapabilitiesFunded

On-site · London

Senior · 5+ yrs · £101K – £192K • Offers Equity · 3mo ago

Agent Runtime & Systems - Member of Technical Staff
Distributed SystemsAPI Design+9 more
View role
Apply