{"id":3685071,"url":"https://alion.io/job/physicsx-platform-engineer-self-hosting-llms-built-with-go","title":"Platform Engineer - Self Hosting LLMs","company":{"id":251,"name":"PhysicsX","domain":"physicsx.ai","url":"https://alion.io/company/physicsx","size_band":"201-500","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Greenhouse","truth_index":{"grade":"B","score":82,"open_postings":36,"ghost_share":0.222,"stale_share":0,"repost_share":0,"time_to_fill_p50_days":98,"computed_at":"2026-11-08T05:47:12Z"}},"role":"DevOps","role_family":"DevOps","seniority":null,"employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["London, United Kingdom"],"countries":["GB"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"C++","optional":false},{"name":"KServe","optional":false},{"name":"Kubernetes","optional":false},{"name":"KV Cache","optional":false},{"name":"Linux","optional":false},{"name":"LLM","optional":false},{"name":"Ollama","optional":false},{"name":"OpenAI","optional":false},{"name":"Post-training","optional":false},{"name":"Python","optional":false},{"name":"Rust","optional":false},{"name":"SGLang","optional":false},{"name":"Speculative Decoding","optional":false},{"name":"vLLM","optional":false},{"name":"CUDA","optional":true},{"name":"Mixture of Experts","optional":true}],"status":"live","first_seen_at":"2026-11-03T10:10:12Z","employer_posted_date":"2026-11-04","last_verified_at":"2026-11-08T21:18:22Z","board_verified":true,"closed_at":null,"days_open":5,"trust":{"level":"ok","repost_count":0,"flags":["company_stale"],"days_open":4},"description":"About us\nRe-architecting Engineering for the Age of Intelligence\n\nPhysicsX 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.\nThe role\nYou 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.\nWe 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.\nYou 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.\nIn 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.\nWhat you will do\nMake self-hosted serving and model routing work in air-gapped deployments, including sites where the hardware, connectivity and operational setup force constrained solutions.\nOwn LLM packaging, registration, deployment, health checks, upgrades, rollback and retirement for supported LLMs.\nEvaluate and integrate serving platforms such as KServe, including inference services, serving runtimes, model loading and rollout controls.\nDefine, model, and implement service levels for availability, quality, and performance metrics (e.g. time to first token, inter-token latency, and tail latency).\nMeasure and improve throughput, GPU utilisation, memory use and cost per token under representative agent workloads.\nTune continuous and chunked batching, KV and prefix caching, quantisation, speculative decoding and tensor, data or expert parallelism where appropriate.\nEvaluate advanced techniques such as cache-aware routing and prefill/decode disaggregation when workload evidence justifies their complexity.\nBuild autoscaling, admission control and capacity management around GPU and serving signals rather than generic CPU metrics.\nMake every routing decision observable and explainable, and use evaluation evidence before adding specialist routes.\nWork with Research and Post-Training specialists to move candidate and tuned models through evaluation into supported production routes.\nHelp determine how this capability should grow and, over time, shape the team around it.\nWhat you bring\nWhere you need to be strongest\nYou have operated inference engines such as vLLM or SGLang, or serving platforms such as KServe, under production traffic, latency and reliability constraints.\nYou can explain the boundary between serving orchestration and inference execution, including how deployment, scaling and runtime configuration affect performance.\nYou have built or operated model routing across more than one provider, and can explain how you balanced cost, quality, latency, failure and policy.\nYou 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.\nYou understand LLM inference as a systems problem: batching, scheduling, KV-cache behaviour, memory pressure, model parallelism and GPU utilisation.\nYou have built and operated GPU workloads on Kubernetes, including deployment, scaling, observability and failure recovery.\nYou can turn fast-moving open-source engines and provider APIs into a supportable product with versioning, compatibility testing, rollback and clear operational boundaries.\nYou are a strong systems engineer who remains hands-on in architecture, implementation, profiling and production debugging.\nYour experience goes materially beyond local model runners or demonstrations; tools such as Ollama are not a substitute for production serving ownership.\nFoundations\nStrong Python plus a systems language such as Go, Rust or C++.\nLinux, containers, Kubernetes, networking, storage and distributed-systems fundamentals.\nGPU observability and performance analysis across engine, system and accelerator metrics.\nModel formats, quantisation, tokenisation and OpenAI-compatible serving APIs.\nTraffic management, streaming, overload protection, health checking and failure recovery.\nIntegration with existing identity, authorisation, secrets and workload-isolation systems.\nClear technical writing, design review, incident response and cross-team communication.\nNice to have\nContributions to KServe, vLLM, SGLang or adjacent inference, gateway or orchestration projects.\nExperience modifying engine internals, profiling kernels or diagnosing CUDA and collective-communication issues.\nExperience with mixture-of-experts models, expert parallelism, speculative decoding or disaggregated serving.\nExperience routing by data-sensitivity policy, evaluation signals or multi-model review workflows.\nExperience with model serving in customer-operated, regulated or fully disconnected environments.\nFamiliarity with Kata Containers, confidential computing or strong multi-workload isolation.\nExperience integrating serving with post-training rollouts and evaluation workloads.\nWe 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. \nWe 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.","description_format":"text","description_chars":6900,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"bachelor","optional":false},"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Simulation & Digital Twin Software","Industrial AI","AI for Science"],"lifecycle":[{"event":"open","at":"2026-11-03T14:38:50Z"}],"visa":[{"country":"GB","licensed_sponsor":true,"adverts_offering_sponsorship_24m":0,"sanctioned_now":false,"evidence":"Licensed UK visa sponsor (Skilled Worker)","filings_12m":null,"filings_prev_12m":null,"green_card_filings_12m":null,"median_offered_wage_usd":null,"route":"Skilled Worker","cap_exempt":false,"checked_at":"2026-11-08T10:45:15+00:00","sources":["UK Home Office: register of licensed sponsors (workers)"],"filings_for_role_12m":0}],"liveness":{"score":90,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.903,"p_room":1,"age_days":4,"expected_fill_days":98,"reasons":["conf:0","velocity","win:early"],"computed_at":"2026-11-08T05:47:12Z"},"pay":null,"html_url":"https://alion.io/job/physicsx-platform-engineer-self-hosting-llms-built-with-go","json_url":"https://alion.io/job/physicsx-platform-engineer-self-hosting-llms-built-with-go.json","meta":{"generated_at":"2026-11-08T21:54:20Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":45684,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-09T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.1,"usd":0.01,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":251},"rest":"https://alion.io/mcp/rest/get_company?id=251"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fphysicsx-platform-engineer-self-hosting-llms-built-with-go"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":2,"usd":0.2},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Fphysicsx-platform-engineer-self-hosting-llms-built-with-go"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.1,"usd":0.01},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Fphysicsx-platform-engineer-self-hosting-llms-built-with-go"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/physicsx-platform-engineer-self-hosting-llms-built-with-go\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fphysicsx-platform-engineer-self-hosting-llms-built-with-go"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":3685071}},{"tool":"search_jobs","arguments":{"company":"physicsx.ai","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":3685071},"note":"people open to offers who fit this vacancy"}],"note":"The same data through MCP tools: https://alion.io/mcp/open needs no sign-in (compact searches, postings, people); https://alion.io/mcp with an Alion account has everything. Docs: https://alion.io/developers"}}