{"id":1212435,"url":"https://alion.io/job/rebellions-npu-software-engineer-sdk","title":"NPU Software Engineer - SDK","company":{"id":173,"name":"Rebellions","domain":"rebellions.ai","url":"https://alion.io/company/rebellions","size_band":"501-1000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Greeting","truth_index":{"grade":"C","score":66,"open_postings":28,"ghost_share":0.571,"stale_share":0,"repost_share":0,"time_to_fill_p50_days":null,"computed_at":"2026-09-26T05:45:00Z"}},"role":"Backend","role_family":"Backend","seniority":"senior","employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Seongnam, South Korea"],"countries":["KR"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":59000,"max_usd":155000,"period":"year","method":"global_role_cell_scaled_by_country","sample_n":4445},"experience_years_min":5,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"Apache TVM","optional":false},{"name":"Buildkite","optional":false},{"name":"C++","optional":false},{"name":"CI/CD","optional":false},{"name":"CUDA","optional":false},{"name":"CUDA Toolkit","optional":false},{"name":"Diffusers","optional":false},{"name":"Docker","optional":false},{"name":"GitHub Actions","optional":false},{"name":"Hugging Face","optional":false},{"name":"JAX","optional":false},{"name":"Kubernetes","optional":false},{"name":"LLM","optional":false},{"name":"MLIR","optional":false},{"name":"Multimodal AI","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"PyTorch C++","optional":false},{"name":"TensorFlow","optional":false},{"name":"TensorFlow C++","optional":false},{"name":"TensorRT","optional":false},{"name":"TensorRT-LLM","optional":false},{"name":"Transformers","optional":false},{"name":"Triton","optional":false},{"name":"vLLM","optional":false}],"status":"live","first_seen_at":"2026-07-10T00:36:52Z","employer_posted_date":"2026-09-25","last_verified_at":"2026-09-25T08:02:56Z","board_verified":true,"closed_at":null,"days_open":79,"trust":{"level":"ok","repost_count":0,"flags":["company_stale"],"days_open":78},"description":"The NPU SDK part of Software Team owns the end-to-end SDK user experience: modeling work to bring state-of-the-art AI models (LLM, Multi-modal, Vision, Speech, etc.) onto Rebellions NPU, building and operating CI/CD pipelines to ship a production-ready SDK to external users, releasing and distributing the software, and authoring and publishing developer documentation.\nResponsibilities and Opportunities\nSDK Ecosystem & Release Pipeline: Design, build, and operate CI/CD pipelines that automate and scale the SDK release process\nModel Deployment & Porting: Port and optimize the latest deep learning models (LLM, Multi-modal, etc.) onto Rebellions NPU, analyze performance bottlenecks, and validate numerical parity against GPU reference implementations when needed\nFramework Integration: Integrate the SDK tightly with the open-source inference and serving ecosystem, including Hugging Face Transformers, Diffusers, vLLM, and to maximize the developer experience\nVerification & Debugging: Design model-feeding frameworks and debugging utilities to ensure functional correctness and long-term stability of the SDK\nDeveloper Documentation: Author and maintain developer-facing documentation - API references, tutorials, model support matrices, and release notes - and operate the documentation build and publishing pipeline for external developers and partners\nKey Qualifications\nMaster’s degree or above in Computer Science, Electrical Engineering, or a related field\nDeep working knowledge of CI/CD tools such as GitHub Actions, Airflow, and Buildkite\nDeep understanding of modern deep learning model architectures, including LLMs (Transformer family), Multi-modal, Vision, and Speech\nStrong familiarity with PyTorch internals, including model customization and graph transformations\nHigh-performance software development skills in Python and Modern C++ (C++17 or later)\nExperience using and integrating major open-source libraries such as Hugging Face (Transformers, Diffusers) and vLLM\nHands-on experience with Python and Kubernetes-based environments for deploying and troubleshooting AI inference workloads in production\nIdeal Qualifications\n5+ years of relevant industry experience, or equivalent practical expertise\nExperience optimizing and deploying models on specific hardware using CUDA, TensorRT, TensorRT-LLM, MLIR, Triton, or TVM\nExperience building scalable ML infrastructure with Docker and Kubernetes\nExperience in AI Harness Engineering - designing environments where AI agents operate autonomously within defined constraints, feedback loops, and system contexts\nContributions to open-source projects as a maintainer or regular contributor\nUnderstanding of the internals of other frameworks such as JAX or TensorFlow\n전형절차\n서류전형 > On-line 인터뷰 > On-site 인터뷰(과제 포함) > Culture-fit인터뷰 > 처우 협의 > 최종 합격\n전형절차는 직무별로 다르게 운영될 수 있으며, 일정 및 상황에 따라 변동될 수 있습니다.\n전형 일정 및 결과는 지원 시 작성하신 이메일로 개별 안내드립니다.\n참고사항\n본 공고는 모집 완료 시 조기 마감될 수 있습니다.\n지원서 내용 중 허위사실이 있는 경우에는 합격이 취소될 수 있습니다.\n채용 및 업무 수행과 관련하여 요구되는 법령 상 자격이 갖추어지지 않은 경우 채용이 제한될 수 있습니다.\n보훈 대상자 및 장애인 여부는 채용 과정에서 어떠한 불이익도 미치지 않습니다.\n담당 업무 범위는 후보자의 전반적인 경력과 경험 등 제반사정을 고려하여 변경될 수 있습니다. 이러한 변경이 필요할 경우, 최종 합격 통지 전 적절한 시기에 후보자와 커뮤니케이션 될 예정입니다.\n채용 관련 문의사항은 아래 메일 주소로 문의바랍니다. \n","description_format":"text","description_chars":3239,"description_truncated":false,"requirements":{"experience_years_min":5,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"master","optional":false},"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Processors, MCUs & AI Chips","AI Compute & Inference","AI Chips & Accelerators"],"lifecycle":[{"event":"open","at":"2026-09-25T05:02:56Z"}],"liveness":{"score":13,"band":"cold","label":"Long shot","p_open":1,"p_active":0.45,"p_room":0.28,"age_days":78,"expected_fill_days":39,"reasons":["conf:21","stale_co","velocity","win:tail","crowd:"],"computed_at":"2026-09-26T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/rebellions-npu-software-engineer-sdk","json_url":"https://alion.io/job/rebellions-npu-software-engineer-sdk.json","meta":{"generated_at":"2026-09-27T04:08:39Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","usage":{"tier":"crawler","counted_by":"address","units_charged":1,"used_today":3894,"day_limit":5000,"remaining_today":1106,"minute_limit":60,"resets_at":"2026-09-28T00:00:00Z"}}}