{"id":91415,"date":"2026-08-21T22:08:27","date_gmt":"2026-08-21T22:08:27","guid":{"rendered":"https:\/\/www.monmouth.edu\/career-development\/job\/software-engineer-ai-framework-2\/"},"modified":"2026-09-21T20:36:22","modified_gmt":"2026-09-22T00:36:22","slug":"software-engineer-ai-framework-2","status":"publish","type":"ch_job","link":"https:\/\/www.monmouth.edu\/career-development\/job\/software-engineer-ai-framework-2\/","title":{"rendered":"Software Engineer, AI Framework"},"content":{"rendered":"<p><strong>About <\/strong><a target=\"_blank\" href=\"https:\/\/bst.ai\/\"><strong><u>Black SesameTechnologies<\/u><\/strong><\/a>\u00a0<\/p>\n<p>Founded in July 2016, Black Sesame Technologies is a leading supplier of automotive-grade intelligent vehicle computing chips and chip-based solutions. Our team has pioneered new chip designs and systems to accelerate deep learning applications for AD and ADAS. We innovate across the entire stack, from chip design to cutting-edge machine learning algorithms, creating revolutionary solutions that balance performance, power, and flexibility.<\/p>\n<p>Our focus on building a co-designed hardware-software ecosystem ensures scalability and quality at every level. Join us as we revolutionize autonomous driving technologies from the ground up.<\/p>\n<p><strong>Job description:<\/strong><\/p>\n<p>We are looking for an experienced AI\/ML engineer passionate about deploying LLM inference frameworks, full-stack model performance attribution, and hardware-software co-design. You might be an ideal candidate if you are seeking to work across the entire inference stack, from framework and compiler down to runtime, firmware, and silicon, to determine how efficiently state of the art AI models run on BST Intelligence processors, and to shape what the next generation of those processors should be.<\/p>\n<p><strong>Responsibilities:<\/strong><\/p>\n<p>Deploy and optimize LLM inference on edge accelerators, spanning model export, graph compilation, and runtime execution.<\/p>\n<p>Attribute end-to-end latency across compiler, runtime, firmware, and memory subsystems; quantify the gap against roofline and bandwidth-bound ceilings.<\/p>\n<p>Build profiling instrumentation and measurement methodology that expose device-side behavior beyond host wall-clock.<\/p>\n<p>Apply quantization, sparsity, and low-precision techniques; characterize the accuracy, latency, and power trade-offs of each.<\/p>\n<p>Stay up to date with the latest research in model architectures and inference acceleration, and translate emerging techniques into hardware requirements for next-generation accelerators.<\/p>\n<p><strong>Qualifications:<\/strong><\/p>\n<p>MS, or Ph.D. degree in Computer Science, Computer Engineering, Applied Math, or related field.\u00a0<\/p>\n<p>You\u00a0can\u00a0work independently, define project goals and scope, and lead your own development effort.\u00a0<\/p>\n<p>Strong Python or C++\/C programming and software design skills, including debugging, performance analysis, and test design.\u00a0<\/p>\n<p>Working knowledge of computer architecture: memory hierarchy, DMA, arithmetic intensity, and roofline analysis.<\/p>\n<p>Experience with deep learning frameworks such as PyTorch, and with at least one inference runtime such as TensorRT, TensorRT-LLM, vLLM.<\/p>\n<p><strong>Ways to stand out from the crowd:\u00a0<\/strong><\/p>\n<p>Experience with trace-based profiling tools such as Nsight Systems, Perfetto, or vendor NPU tooling<\/p>\n<p>Familiarity with LLM inference such as KV cache management, speculative decoding, and attention kernels<\/p>\n<p>Experience with AI compilers, including graph optimization, tiling, and quantization passes<\/p>\n<p>Firmware or embedded systems experience on an accelerator<\/p>\n<p>Experience in model deployment within the autonomous driving industry<\/p>\n<p>Experience deploying LLMs on edge devices<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"_ch_employer_id":"14029","_ch_external_id":"11336738","_ch_location_state":"","_ch_location_city":"","_ch_is_ocr_job":"","_ch_expiration_date":"2026-10-21","_ch_apply_link":"https:\/\/monmouth.joinhandshake.com\/jobs\/11336738\/share_preview"},"ch_stakeholder":[],"ch_class_year":[],"ch_job_category":[86],"ch_career_skill":[],"ch_industry":[65],"class_list":["post-91415","ch_job","type-ch_job","status-publish","hentry","ch_job_category-full-time","ch_industry-science-technology-innovation"],"_links":{"self":[{"href":"https:\/\/www.monmouth.edu\/career-development\/wp-json\/wp\/v2\/ch_job\/91415","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.monmouth.edu\/career-development\/wp-json\/wp\/v2\/ch_job"}],"about":[{"href":"https:\/\/www.monmouth.edu\/career-development\/wp-json\/wp\/v2\/types\/ch_job"}],"wp:attachment":[{"href":"https:\/\/www.monmouth.edu\/career-development\/wp-json\/wp\/v2\/media?parent=91415"}],"wp:term":[{"taxonomy":"ch_stakeholder","embeddable":true,"href":"https:\/\/www.monmouth.edu\/career-development\/wp-json\/wp\/v2\/ch_stakeholder?post=91415"},{"taxonomy":"ch_class_year","embeddable":true,"href":"https:\/\/www.monmouth.edu\/career-development\/wp-json\/wp\/v2\/ch_class_year?post=91415"},{"taxonomy":"ch_job_category","embeddable":true,"href":"https:\/\/www.monmouth.edu\/career-development\/wp-json\/wp\/v2\/ch_job_category?post=91415"},{"taxonomy":"ch_career_skill","embeddable":true,"href":"https:\/\/www.monmouth.edu\/career-development\/wp-json\/wp\/v2\/ch_career_skill?post=91415"},{"taxonomy":"ch_industry","embeddable":true,"href":"https:\/\/www.monmouth.edu\/career-development\/wp-json\/wp\/v2\/ch_industry?post=91415"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}