{"id":168360,"url":"https://alion.io/job/eka-care-senior-data-scientist-kernel-optimisation-inference-engineer","title":"Senior Data Scientist ( Kernel Optimisation & Inference Engineer)","company":{"id":59359,"name":"Eka Care","domain":"eka.care","url":"https://alion.io/company/eka-care","size_band":"11-50","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Keka","truth_index":{"grade":"B","score":75,"open_postings":7,"ghost_share":0,"stale_share":1,"repost_share":0,"time_to_fill_p50_days":null,"computed_at":"2026-10-16T05:45:00Z"}},"role":"Data Science","role_family":"Data Science","seniority":"senior","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Bengaluru, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":24000,"max_usd":50000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":59},"experience_years_min":2,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AWQ","optional":false},{"name":"CUDA","optional":false},{"name":"CUDA Toolkit","optional":false},{"name":"Edge AI","optional":false},{"name":"GPTQ","optional":false},{"name":"Mixture of Experts","optional":false},{"name":"Perplexity","optional":false},{"name":"SGLang","optional":false},{"name":"Speculative Decoding","optional":false},{"name":"TensorRT-LLM","optional":false},{"name":"vLLM","optional":false},{"name":"TensorRT","optional":true}],"status":"live","first_seen_at":"2026-08-10T10:25:23Z","employer_posted_date":"2026-08-10","last_verified_at":"2026-10-16T15:32:18Z","board_verified":true,"closed_at":null,"days_open":67,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":67},"description":"Kernel Optimisation & Inference Engineer\nBengaluru · Full-time · 2-5 yrs\nSomewhere between the model and the silicon, 10-20% of a training budget goes missing. Your job is to go get it back, and then make the same model fast enough to run in a clinic, and small enough to run on a phone.\nAbout EkaCare and the mission\nEkaCare is India's connected healthcare platform: an EMR that doctors run their practices on, a personal health record used by millions of Indians, and one of the deepest integrations with India's ABDM digital-health rails. Our Parrotlet family of medical models already serves Indian doctors in production, and we open-source our work where it counts.\nThe role:\nYou'll work with our performance lead on making everything fast: training-side fused kernels and MFU on the 30B MoE, inference-side latency and throughput, and the quantised 2B/4B on-device tier. Hardware-up: profiler first, roofline reasoning always, custom kernels when the math says so.\nWhat you'll do\nProfile training and inference workloads and hunt utilisation gaps across kernels, memory and comms.\nWrite and tune CUDA kernels where existing ops leave real performance on the table, and know when they don't.\nOptimise MoE-specific paths: grouped GEMMs, all-to-all communication, expert load imbalance.\nBuild the fast inference path: vLLM-class serving, continuous batching, prompt/prefix caching for clinical-context workloads, speculative decoding.\nOwn quantisation for the 2B/4B variants (AWQ/GPTQ-class, fp8) - with eval-parity verification, not just perplexity.\nMake on-device inference real for the hardware Indian clinics actually have.\nWhat we look for\n2-5 years in GPU performance work; you've profiled real workloads and shipped optimisations with before/after numbers you can defend.\nWorking fluency in CUDA, and memory-hierarchy reasoning (coalescing, occupancy, SRAM tiling; you can explain *why* FlashAttention is fast).\nHands-on with a modern serving stack (vLLM, TensorRT-LLM, SGLang or similar) beyond just running it.\nMeasurement discipline: you profile before optimising and verify correctness after.\nBonus\nfp8 experience on H100/H200-class hardware; torch.compile/inductor internals.\nQuantisation research or on-device/mobile inference experience.\nOpen-source kernels or serving contributions.\nWhy this is a rare gig\nOpen source, with your name on it: weights and technical reports ship publicly.\nIndia-scale mission: models for a billion people in their own languages.\nCompute that’s rare to fine: dedicated multi-node H200 training under a national grant.\nSmall senior team: you work with the people who own the recipe.\nA live deployment path: Government institutes, EkaCare's doctors and patients use what you ship.\nFull-Time Employee Benefits\nMedical Insurance & Accidental Insurance\nMaternity & Paternity Benefits\nPF, Gratuity, & Leave Encashment\nSalary Advance Policy","description_format":"text","description_chars":2880,"description_truncated":false,"requirements":{"experience_years_min":2,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":["Accidental insurance","Dental insurance","Health insurance"],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["EHR & Clinical Software","Practice Management Software","Consumer Health Apps"],"lifecycle":[{"event":"open","at":"2026-08-10T10:25:23Z"}],"visa":[],"liveness":{"score":11,"band":"cold","label":"Long shot","p_open":1,"p_active":0.386,"p_room":0.28,"age_days":66,"expected_fill_days":31,"reasons":["conf:3","velocity","win:tail","crowd:"],"computed_at":"2026-10-16T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/eka-care-senior-data-scientist-kernel-optimisation-inference-engineer","json_url":"https://alion.io/job/eka-care-senior-data-scientist-kernel-optimisation-inference-engineer.json","meta":{"generated_at":"2026-10-16T18:26:43Z","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":3530,"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":59359},"rest":"https://alion.io/mcp/rest/get_company?id=59359"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Feka-care-senior-data-scientist-kernel-optimisation-inference-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%2Feka-care-senior-data-scientist-kernel-optimisation-inference-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%2Feka-care-senior-data-scientist-kernel-optimisation-inference-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/eka-care-senior-data-scientist-kernel-optimisation-inference-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Feka-care-senior-data-scientist-kernel-optimisation-inference-engineer"}]}