{"id":196459,"url":"https://alion.io/job/antino-mlops-engineer","title":"MLOps Engineer","company":{"id":9454,"name":"Antino","domain":"antino.com","url":"https://alion.io/company/antino","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":null,"truth_index":null},"role":"AI/ML","role_family":"AI/ML","seniority":null,"employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Gurgaon, 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":"AWS","optional":false},{"name":"Azure","optional":false},{"name":"CI/CD","optional":false},{"name":"CUDA","optional":false},{"name":"GCP","optional":false},{"name":"LLM","optional":false},{"name":"Machine Learning","optional":false}],"status":"live","first_seen_at":"2026-09-03T13:00:12Z","employer_posted_date":null,"last_verified_at":"2026-09-03T13:00:12Z","board_verified":false,"closed_at":null,"days_open":50,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":50},"description":"We are seeking a Senior MLOps / LLM Infrastructure Engineer to drive the deployment, distributed training, and infrastructure optimization of large-scale machine learning models. In this role, you will bridge the gap between AI development and production systems, ensuring high GPU utilization, scalable performance, cost efficiency, and cloud-agnostic architectures for models up to 20B parameters.\nResponsibilities:\nDeploy and manage ML/LLM models (< 20B parameters) in production environments.\nDesign and execute model load testing and performance benchmarking (latency, throughput, memory, cost).\nBuild and optimize multi-node, multi-GPU training pipelines.\nConfigure and tune distributed training frameworks (data parallelism, model parallelism, and pipeline parallelism).\nOptimize GPU utilization, memory footprint, and inference costs.\nSet up CI/CD pipelines for model deployment and retraining.\nTroubleshoot GPU, networking, and performance bottlenecks.\nWork across cloud platforms to ensure portability and vendor-agnostic deployments.\nRequirements:\nStrong experience with GPU workloads (NVIDIA GPUs, CUDA concepts).\nProven expertise in model deployment on AWS, Azure, and GCP.\nHands-on experience deploying models up to 20B parameters.\nExperience with distributed training (multi-node, multi-GPU setups).\nDeep understanding of load testing, stress testing, and benchmarking ML systems.","description_format":"text","description_chars":1395,"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":["IT Consulting & Digital Transformation","IT Outsourcing & Dedicated Teams","Custom Software Development","AI Consulting & Integration"],"lifecycle":[{"event":"open","at":"2026-09-03T13:00:12Z"}],"visa":[],"liveness":{"score":5,"band":"cold","label":"Long shot","p_open":0.4,"p_active":0.359,"p_room":0.35,"age_days":49,"expected_fill_days":21,"reasons":["seen:49","velocity","win:tail"],"computed_at":"2026-10-23T05:54:15Z"},"pay":null,"html_url":"https://alion.io/job/antino-mlops-engineer","json_url":"https://alion.io/job/antino-mlops-engineer.json","meta":{"generated_at":"2026-10-23T16:01:32Z","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":24217,"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":9454},"rest":"https://alion.io/mcp/rest/get_company?id=9454"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fantino-mlops-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%2Fantino-mlops-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%2Fantino-mlops-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/antino-mlops-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fantino-mlops-engineer"}]}