---
title: 'Platform Engineer - Self Hosting LLMs at PhysicsX'
canonical: 'https://feeny.ai/job/platform-engineer-self-hosting-llms-physicsx-london-e21a8r33hznz'
type: 'job'
last_seen: '2026-11-05'
---

# Platform Engineer - Self Hosting LLMs at PhysicsX

- **Company:** PhysicsX
- **Location:** London, United Kingdom
- **Posted:** 2026-11-03
- **Last confirmed live:** 2026-11-05
- **Apply:** https://job-boards.eu.greenhouse.io/physicsx/jobs/5025659101

## Job description

## About us

Re-architecting Engineering for the Age of Intelligence

PhysicsX is the physics AI company for industrials. The company’s mission is to accelerate hardware innovation by overhauling what industrial engineering and manufacturing look like today. PhysicsX is building a new simulation software stack to deliver deep physics AI enablement across the entire engineering lifecycle. The company partners with leading organisations in aerospace & defence, automotive, semiconductors, materials, and energy & renewables, supporting them on some of their most critical and complex challenges. PhysicsX is headquartered in the United Kingdom, with offices in London, New York, and Singapore and an expanding presence in the Bay Area.

## The role

You will build the LLM access layer for agents on the PhysicsX platform. That layer serves self-hosted open models and routes each task to the model, or combination of models, that best fits its constraints.

We want to bring deep, production experience in self-hosted LLM serving and model routing into PhysicsX. You will establish the capability to run open models reliably and choose between self-hosted and external models according to the needs of each workload. You will set the technical direction for inference engines such as vLLM and SGLang, and serving platforms such as KServe. You will build foundations that product, delivery and customer teams can rely on.

You will own both. You will learn our requirements and define the implementation, rather than inherit a prescribed gateway design. You will wire serving and routing into the existing platform, identity and observability systems.

In the near term, you’ll make the platform’s agentic capabilities work out of the box, with no customer-supplied API key needed. Longer term, you’ll build the serving layer into a flexible routing foundation that balances competing priorities, such as cost, quality and data sensitivity, as our needs change.

## What you will do

- Make self-hosted serving and model routing work in air-gapped deployments, including sites where the hardware, connectivity and operational setup force constrained solutions.
- Own LLM packaging, registration, deployment, health checks, upgrades, rollback and retirement for supported LLMs.
- Evaluate and integrate serving platforms such as KServe, including inference services, serving runtimes, model loading and rollout controls.
- Define, model, and implement service levels for availability, quality, and performance metrics (e.g. time to first token, inter-token latency, and tail latency).
- Measure and improve throughput, GPU utilisation, memory use and cost per token under representative agent workloads.
- Tune continuous and chunked batching, KV and prefix caching, quantisation, speculative decoding and tensor, data or expert parallelism where appropriate.
- Evaluate advanced techniques such as cache-aware routing and prefill/decode disaggregation when workload evidence justifies their complexity.
- Build autoscaling, admission control and capacity management around GPU and serving signals rather than generic CPU metrics.
- Make every routing decision observable and explainable, and use evaluation evidence before adding specialist routes.
- Work with Research and Post-Training specialists to move candidate and tuned models through evaluation into supported production routes.
- Help determine how this capability should grow and, over time, shape the team around it.

## What you bring

Where you need to be strongest

- You have operated inference engines such as vLLM or SGLang, or serving platforms such as KServe, under production traffic, latency and reliability constraints.
- You can explain the boundary between serving orchestration and inference execution, including how deployment, scaling and runtime configuration affect performance.
- You have built or operated model routing across more than one provider, and can explain how you balanced cost, quality, latency, failure and policy.
- You can describe the serving architecture you operated, the bottlenecks you found, the changes you made and the measured effect on latency, throughput, reliability or cost.
- You understand LLM inference as a systems problem: batching, scheduling, KV-cache behaviour, memory pressure, model parallelism and GPU utilisation.
- You have built and operated GPU workloads on Kubernetes, including deployment, scaling, observability and failure recovery.
- You can turn fast-moving open-source engines and provider APIs into a supportable product with versioning, compatibility testing, rollback and clear operational boundaries.
- You are a strong systems engineer who remains hands-on in architecture, implementation, profiling and production debugging.
- Your experience goes materially beyond local model runners or demonstrations; tools such as Ollama are not a substitute for production serving ownership.

Foundations

- Strong Python plus a systems language such as Go, Rust or C++.
- Linux, containers, Kubernetes, networking, storage and distributed-systems fundamentals.
- GPU observability and performance analysis across engine, system and accelerator metrics.
- Model formats, quantisation, tokenisation and OpenAI-compatible serving APIs.
- Traffic management, streaming, overload protection, health checking and failure recovery.
- Integration with existing identity, authorisation, secrets and workload-isolation systems.
- Clear technical writing, design review, incident response and cross-team communication.

## Nice to have

- Contributions to KServe, vLLM, SGLang or adjacent inference, gateway or orchestration projects.
- Experience modifying engine internals, profiling kernels or diagnosing CUDA and collective-communication issues.
- Experience with mixture-of-experts models, expert parallelism, speculative decoding or disaggregated serving.
- Experience routing by data-sensitivity policy, evaluation signals or multi-model review workflows.
- Experience with model serving in customer-operated, regulated or fully disconnected environments.
- Familiarity with Kata Containers, confidential computing or strong multi-workload isolation.
- Experience integrating serving with post-training rollouts and evaluation workloads.

We value diversity and are committed to equal employment opportunity regardless of sex, race, religion, ethnicity, nationality, disability, age, sexual orientation or gender identity. We strongly encourage individuals from groups traditionally underrepresented in tech to apply. To help make a change, we sponsor bright women from disadvantaged backgrounds through their university degrees in science and mathematics.

We collect diversity and inclusion data solely for the purpose of monitoring the effectiveness of our equal opportunities policies and ensuring compliance with employment and equality legislation. This information is confidential, used only in aggregate form, and will not influence the outcome of your application.

## About PhysicsX

## Company Overview
- **One-liner**: PhysicsX builds an AI-native software stack for physics simulation and engineering design, enabling advanced industries to accelerate innovation by orders of magnitude.
- **Entity Type**: Private (Series C)
- **Headquarters**: London, United Kingdom
- **Founded**: 2019
- **Founders**: Jacomo Corbo (CEO & Co-Founder) and a Co-Founder & Chairman

## Core Business
- **Primary industries**: Aerospace & Defense, Automotive, Semiconductors, Materials, Energy & Renewables
- **Target customers**: Large industrial organizations (B2B Enterprise) – engineers and teams designing and operating complex physical systems
- **Mission**: Empower industrial organizations to build beyond human imagination and address the defining challenges of our time, with a focus on climate and human health impact

## Products & Services
- **PhysicsX Platform** (SaaS + embedded engineering): An AI-native software stack that unifies simulation, physics AI, data, and engineering applications. Integrates with existing toolchains (CAD, CAE, PLM) and accelerates simulation by orders of magnitude, enabling engineers to explore larger design spaces and move from concept to validated design in days.

## Market Standing
- **Valuation**: Approximately $2.4B (as of Series C in August 2026)
- **Key Metric**: Total funding ~$487M (including $300M Series C, $135M Series B, $32M Series A, $20M from NVentures). Revenue is generating but not publicly disclosed (LinkedIn estimates ~$1M, but company is early-stage revenue generating).
- **Notable Investors/Partners**: Atomico (led Series B), General Catalyst (led Series A), NVentures (NVIDIA’s venture arm), NVIDIA (strategic partner), Siemens (collaboration on data center power infrastructure)
- **Growth Signals**: 
  - Series C oversubscribed $300M at $2.4B valuation (Aug 2026)
  - Headcount growth of 71% YoY (LinkedIn: 226 employees; PitchBook: 350 employees post-C)
  - Forward-deployed engineers embedded in customer programs
  - Open standards for physics AI powered by NVIDIA (March 2026)

## Competitive Advantages
- **True AI-native platform**: Physics AI is built as a core primitive, not bolted onto legacy tooling. Uses advanced models like Fourier Neural Operators to simulate physics at speeds unattainable with traditional CFD/FEA.
- **Embedded deployment model**: Forward-deployed engineers work alongside customers on live problems, ensuring measurable outcomes and deep domain integration.
- **Focus on hardest problems**: Targets extreme complexity (aerospace, semiconductors, climate tech) where speed of development is critical and margins for error are zero.
- **Strategic partnerships**: Deep collaboration with NVIDIA (compute, open standards) and Siemens (infrastructure AI).

## Strategic Focus
- Continue scaling the platform across multiple industrial verticals, with emphasis on the climate transition (energy, materials efficiency) and human health (medical devices, supply chain).
- Expand the "Large Physics Models" research program and open standards initiatives.
- Grow the global team (currently 350+ across UK and US) with strong emphasis on research, product engineering, and forward deployment.

## Why Work Here
- **Culture**: Grounded visionaries, moving fast with trust and ambition. Values include "we make stuff happen" and "we form a community in which people can grow."
- **Work environment**: Hybrid (2-3 days in office per week); offices in London (Shoreditch) and New York (Downtown Manhattan). Visa sponsorship and relocation support available.
- **Benefits**: Generous pension contributions, health insurance, enhanced parental support, development opportunities.
- **Engineering culture**: Work on the hardest problems in industry – physics, AI, and engineering collide. Small, high-autonomy teams. Interview process includes pairing and in-person final rounds.
- **Diversity**: Committed to equal opportunities; strongly encourages underrepresented groups to apply.

## Sources
1. [PhysicsX.ai](https://www.physicsx.ai/) – company website
2. [PhysicsX About](https://www.physicsx.ai/about) – mission, team, challenge
3. [PhysicsX Careers](https://www.physicsx.ai/careers) – culture, benefits, interview process
4. [LinkedIn](https://uk.linkedin.com/company/physicsx) – employee count, funding, headcount growth
5. [PitchBook](https://pitchbook.com/profiles/company/529644-70) – valuation, Series C, founding year

## Other roles at PhysicsX

- [Head of Chemistry](https://feeny.ai/job/head-of-chemistry-physicsx-new-york-nn2v0mz1ebdd) — New York, NY
- [Head of Chemistry](https://feeny.ai/job/head-of-chemistry-physicsx-london-4fm0gnh9danw) — London, United Kingdom
- [Principal Machine Learning Engineer](https://feeny.ai/job/principal-machine-learning-engineer-physicsx-new-york-3d9h60fwps9r) — New York, NY
- [Deployment Strategist](https://feeny.ai/job/deployment-strategist-physicsx-new-york-p6db3byb2a0m) — New York, NY
- [Senior People Operations Manager](https://feeny.ai/job/senior-people-operations-manager-physicsx-new-york-fzc1c1tjtbkn) — New York, NY
- [Platform Support Engineer](https://feeny.ai/job/platform-support-engineer-physicsx-singapore-k3rwa8fcz73f) — Singapore
- [Simulation Engineer (CFD) - Large Physics Models](https://feeny.ai/job/simulation-engineer-cfd-large-physics-models-physicsx-london-4e2nb7eenrxj) — London, United Kingdom
- [Simulation Engineer - Thermal Process](https://feeny.ai/job/simulation-engineer-thermal-process-physicsx-singapore-69rhqzweam43) — Singapore
- [Platform Support Engineer](https://feeny.ai/job/platform-support-engineer-physicsx-new-york-an8gzcdfwjbw) — New York, NY
- [Delivery Engineer](https://feeny.ai/job/delivery-engineer-physicsx-singapore-5wsdrs5mzky7) — Singapore