{"id":2906166,"url":"https://alion.io/job/multicorewareinc-sse-optimization-engineer","title":"SSE - Optimization Engineer","company":{"id":1764592,"name":"Multicorewareinc","domain":"multicorewareinc.com","url":"https://alion.io/company/multicorewareinc","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Zoho Recruit","truth_index":null},"role":"Industrial Engineering","role_family":"Industrial Engineering","seniority":"middle","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":null,"experience_years_min":4,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AWQ","optional":false},{"name":"C++","optional":false},{"name":"GPTQ","optional":false},{"name":"Knowledge Distillation","optional":false},{"name":"KV Cache","optional":false},{"name":"LLM","optional":false},{"name":"LoRA","optional":false},{"name":"Mixture of Experts","optional":false},{"name":"Model Distillation","optional":false},{"name":"ONNX","optional":false},{"name":"PEFT","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"PyTorch C++","optional":false},{"name":"QLoRA","optional":false},{"name":"Quantization","optional":false},{"name":"Transformers","optional":false},{"name":"Apache TVM","optional":true},{"name":"MLIR","optional":true},{"name":"ONNX Runtime","optional":true},{"name":"TensorRT","optional":true}],"status":"live","first_seen_at":"2026-08-30T00:00:00Z","employer_posted_date":"2026-08-30","last_verified_at":"2026-10-21T09:34:39Z","board_verified":true,"closed_at":null,"days_open":52,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":52},"description":"We are looking\nfor a Senior Software Engineer to develop and optimize deep learning models,\nincluding CNNs, LLMs, and MoE, for efficient inference across CPU, GPU,\nhardware accelerators, and edge devices. The role focuses on quantization,\nmodel compression, high-performance kernel implementation, transformer\noptimization, and production deployment.\nResponsibilities:\nDevelop and optimize deep learning models (CNNs,\nLLMs, MoE) for efficient inference across CPU, GPU, hardware accelerators, and\nedge devices.\nDesign and implement quantization algorithms\n(PTQ, QAT, GPTQ, AWQ) from scratch.\nApply model compression techniques such as\npruning, decomposition, and distillation.\nImplement and optimize quantized kernels (INT8,\nINT4, FP8) using C++ for high performance.\nTranslate research papers into production-ready\nimplementations.\nOptimize latency, throughput, and memory usage\nfor real-world deployment.\nWork on transformer optimization including\nKV-cache, PEFT (LoRA/QLoRA), and MoE models.\nProfile, benchmark, and debug model performance\nacross different hardware platforms.\nCollaborate with ML, compiler, and hardware\nteams to deliver optimized solutions.\nRequirements\nEducation:\n\nBE/BTech/MS/MTech in Computer Science or a related field.\nTechnical Skills (Must haves):\n4+ years of relevant experience.\nStrong programming skills in Python and C++.\nProven experience in quantization algorithms\n(PTQ, QAT, GPTQ, AWQ).\nHands-on experience in pruning, model\ncompression, and inference optimization.\nExperience implementing quantization or\noptimization techniques from scratch.\nStrong understanding of CNNs, Transformers, and\nLLM architectures.\nExperience with PyTorch / ONNX and model\ndeployment pipelines.\nStrong problem-solving and performance\noptimization skills.\nNeed to have (Can be bridged):\nNo\nadditional bridged skills were specified.\nGood to have (Not essential):\nExperience with MoE architectures and PEFT\ntechniques (LoRA, QLoRA).\nKnowledge of TensorRT, ONNX Runtime, TVM, and\nMLIR.\nFamiliarity with hardware-aware optimization\nacross GPU, NPU, and edge devices.\nExperience in research paper implementation or\nopen-source contributions.\nPreferred Qualifications (Optional):\nNo\nadditional preferred qualifications were specified.","description_format":"text","description_chars":2241,"description_truncated":false,"requirements":{"experience_years_min":4,"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":[],"lifecycle":[{"event":"open","at":"2026-10-20T07:54:24Z"}],"visa":[],"liveness":{"score":17,"band":"cold","label":"Long shot","p_open":1,"p_active":0.481,"p_room":0.35,"age_days":52,"expected_fill_days":22,"reasons":["conf:0","win:tail"],"computed_at":"2026-10-21T05:46:15Z"},"pay":null,"html_url":"https://alion.io/job/multicorewareinc-sse-optimization-engineer","json_url":"https://alion.io/job/multicorewareinc-sse-optimization-engineer.json","meta":{"generated_at":"2026-10-21T12:11:37Z","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":17326,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-22T00:00:00Z"}},"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":1764592},"rest":"https://alion.io/mcp/rest/get_company?id=1764592"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fmulticorewareinc-sse-optimization-engineer"},{"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%2Fmulticorewareinc-sse-optimization-engineer"},{"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%2Fmulticorewareinc-sse-optimization-engineer"},{"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/multicorewareinc-sse-optimization-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fmulticorewareinc-sse-optimization-engineer"}]}