{"id":834321,"url":"https://alion.io/job/lm-studio-blog-software-engineer-inference-runtime","title":"Software Engineer, Inference Runtime","company":{"id":35399,"name":"LM Studio","domain":"lmstudio.ai","url":"https://alion.io/company/lm-studio-blog","size_band":"11-50","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":null},"role":"Backend","role_family":"Backend","seniority":null,"employment_type":"full_time","work_mode":"hybrid","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["New York, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":150000,"max":350000,"currency":"USD","period":"year","gross":null,"usd_annual":350000},"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":true,"technologies":[{"name":"C++","optional":false},{"name":"CUDA","optional":false},{"name":"CUDA Toolkit","optional":false},{"name":"ExecuTorch","optional":false},{"name":"llama.cpp","optional":false},{"name":"LM Studio","optional":false},{"name":"MLX ML","optional":false},{"name":"Multimodal AI","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"PyTorch C++","optional":false},{"name":"ROCm","optional":false},{"name":"SGLang","optional":false},{"name":"TensorRT-LLM","optional":false},{"name":"vLLM","optional":false},{"name":"TensorRT","optional":true}],"status":"live","first_seen_at":"2026-08-07T23:15:10Z","employer_posted_date":"2026-08-07","last_verified_at":"2026-10-16T09:10:04Z","board_verified":true,"closed_at":null,"days_open":69,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":69},"description":"LM Studio is used by millions of people around the world to run AI on their own computers, and now with Bionic - also in the cloud. Our values prioritize putting the human in the center, and creating tools that we want to use ourselves, and recommend to our friends and family.\nAs a team, we work with high technical intensity and personal responsibility. We are looking for curious, self-motivated, creative, and technically excellent teammates to join us and build the future of human-AI interactions in software.\nThe Role\nWe are looking for an Inference Runtime Software Engineer to push forward LM Studio's inference stack on-device and in the cloud. You will integrate new inference engines and runtime capabilities, bring up new open-weight models and modalities, and optimize model execution for a wide range of CPU and GPU targets. You will also contribute improvements to the open-source projects we build on.\nQualifications\nSignificant experience building production ML systems, inference runtimes, or performance-sensitive infrastructure\n\nStrong programming ability in Python and C++\n\nDeep understanding of transformer architectures and the mechanics of model inference\n\nExperience profiling CPU or GPU workloads and reasoning about compute, memory, synchronization, and data movement\n\nExperience with PyTorch and inference systems such as llama.cpp, MLX, ExecuTorch, vLLM, SGLang, or TensorRT-LLM\n\nStrong debugging instincts across model code, runtime internals, operating systems, and CPU or GPU execution\n\nTakes personal responsibility for the correctness and performance of their work\n\nBonus Qualifications\nPast contributions to open-source inference runtime projects such as llama.cpp, MLX, ExecuTorch, vLLM, SGLang, or TensorRT-LLM\n\nResponsibilities\nMaintain and push forward our inference stack on-device and in the cloud\n\nBring up new model architectures and multimodal models\n\nImprove latency, throughput, memory use, and reliability across CPU, CUDA, Metal, Vulkan, and ROCm runtimes\n\nBuild runtime capabilities for model loading, batching, scheduling, caching, and distributed execution\n\nBenchmark and diagnose correctness and performance problems across the inference stack\n\nContribute upstream to open-source projects such as llama.cpp and MLX\n\nBenefits\nCompetitive salary and equity grants\n\nGreat medical, vision, dental healthcare plans\n\nCatered team lunch / expensed dinners in the office\n\nFlexible PTO\n\nFlexible WFH\n\nSun-drenched office in SoHo in NYC","description_format":"text","description_chars":2479,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":["Equity"],"hiring_locations":[{"name":"United States","iso":"US","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["LLM & Generative AI","AI Development Tools"],"lifecycle":[{"event":"open","at":"2026-09-12T18:14:18Z"}],"visa":[],"liveness":{"score":13,"band":"cold","label":"Long shot","p_open":1,"p_active":0.305,"p_room":0.44,"age_days":69,"expected_fill_days":63,"reasons":["conf:1","win:tail","crowd:"],"computed_at":"2026-10-16T05:45:00Z"},"pay":{"stated_usd_annual":350000,"is_top_pay":true},"html_url":"https://alion.io/job/lm-studio-blog-software-engineer-inference-runtime","json_url":"https://alion.io/job/lm-studio-blog-software-engineer-inference-runtime.json","meta":{"generated_at":"2026-10-16T13:32:12Z","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":12975,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-17T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"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":35399},"rest":"https://alion.io/mcp/rest/get_company?id=35399"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Flm-studio-blog-software-engineer-inference-runtime"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"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%2Flm-studio-blog-software-engineer-inference-runtime"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"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%2Flm-studio-blog-software-engineer-inference-runtime"},{"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/lm-studio-blog-software-engineer-inference-runtime\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Flm-studio-blog-software-engineer-inference-runtime"}]}