{"id":3019122,"url":"https://alion.io/job/zenteiq-performance-engineer-inference-2","title":"Performance Engineer - Inference","company":{"id":1338,"name":"ZenteiQ","domain":"zenteiq.ai","url":"https://alion.io/company/zenteiq-ai","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Keka","truth_index":null},"role":"AI/ML","role_family":"AI/ML","seniority":null,"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":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Python","optional":false},{"name":"SGLang","optional":false},{"name":"TensorRT-LLM","optional":false},{"name":"vLLM","optional":false},{"name":"KV Cache","optional":true},{"name":"Quantization","optional":true},{"name":"TensorRT","optional":true},{"name":"TPU","optional":true}],"status":"live","first_seen_at":"2026-09-25T09:27:46Z","employer_posted_date":"2026-09-25","last_verified_at":"2026-10-23T04:32:16Z","board_verified":true,"closed_at":null,"days_open":27,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":27},"description":"About the Role\nWe are looking for a Performance Engineer, Inference to understand and improve the systems that\nserve our foundation models. Inference is a tightly coupled system spanning model execution, serving\nruntimes, distributed systems, accelerators, scheduling, memory, and reliability. You will measure the\nsystem end to end, identify the highest-leverage performance gaps, and work across teams to close\nthem while preserving correctness.\nResponsibilities\nRun cross-layer performance investigations across throughput, latency, memory efficiency,\nreliability, and cost.\nBuild profiling, benchmarking, and observability tools that make inference performance\nmeasurable and explainable.\nIdentify bottlenecks across model servers, batching and scheduling, distributed execution, memory\nsystems, and accelerators.\nPartner with model, platform, and infrastructure teams to prioritize and land high-impact\noptimizations.\nValidate that performance improvements preserve model quality and numerical correctness.\nMinimum Qualifications\nHands-on experience profiling and optimizing ML systems or other performance-critical production\nsystems.\nProduction experience with at least one modern inference stack such as vLLM, SGLang,\nTensorRT-LLM, NVIDIA Dynamo, or an equivalent serving runtime.\nExperience serving or operating large models across accelerator-backed infrastructure, including\nmulti-GPU or multi-accelerator systems.\nStrong Python skills and the ability to read, instrument, and modify large production codebases.\nSolid understanding of transformer inference, distributed systems, latency/throughput trade-offs,\nand accelerator performance fundamentals.\nPreferred Qualifications\nExperience with large-scale or multi-node inference, including tensor, pipeline, data, or expert\nparallelism.\nExperience with GPUs, TPUs, NPUs, or other ML accelerators and associated profiling tools.\nExperience with quantization, low-precision inference, KV-cache optimization, speculative\ndecoding, or long-context serving.\nExperience contributing to or modifying inference runtimes, kernels, compilers, or distributed\nserving components.\nExperience optimizing inference for constrained or on-device environments.","description_format":"text","description_chars":2203,"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":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Machine Learning","STEM Education","Simulation & Digital Twin Software","AI for Science"],"lifecycle":[{"event":"open","at":"2026-10-21T17:19:33Z"}],"visa":[],"liveness":{"score":38,"band":"fade","label":"Fading","p_open":1,"p_active":0.684,"p_room":0.55,"age_days":27,"expected_fill_days":23,"reasons":["conf:1","velocity","win:tail"],"computed_at":"2026-10-23T05:54:15Z"},"pay":null,"html_url":"https://alion.io/job/zenteiq-performance-engineer-inference-2","json_url":"https://alion.io/job/zenteiq-performance-engineer-inference-2.json","meta":{"generated_at":"2026-10-23T08:58:19Z","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":14403,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-24T00:00:00Z"}},"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":1338},"rest":"https://alion.io/mcp/rest/get_company?id=1338"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fzenteiq-performance-engineer-inference-2"},{"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%2Fzenteiq-performance-engineer-inference-2"},{"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%2Fzenteiq-performance-engineer-inference-2"},{"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/zenteiq-performance-engineer-inference-2\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fzenteiq-performance-engineer-inference-2"}]}