{"id":1289080,"url":"https://alion.io/job/spreeai-principal-engineer-ai-platform-infrastructure","title":"Principal Engineer, AI Platform & Infrastructure","company":{"id":1765982,"name":"SPREEAI","domain":"spreeai.com","url":"https://alion.io/company/spreeai","size_band":"11-50","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Rippling","truth_index":null},"role":"Backend","role_family":"Backend","seniority":"lead","employment_type":"full_time","work_mode":"hybrid","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["San Francisco, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":173000,"max_usd":349000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":861},"experience_years_min":10,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AWS","optional":false},{"name":"AWS Lambda","optional":false},{"name":"Azure","optional":false},{"name":"BentoML","optional":false},{"name":"CI/CD","optional":false},{"name":"CoreWeave","optional":false},{"name":"CUDA","optional":false},{"name":"CUDA Toolkit","optional":false},{"name":"Docker","optional":false},{"name":"Edge AI","optional":false},{"name":"Flyte","optional":false},{"name":"GCP","optional":false},{"name":"KServe","optional":false},{"name":"Kubeflow","optional":false},{"name":"Kubernetes","optional":false},{"name":"Metaflow","optional":false},{"name":"Multimodal AI","optional":false},{"name":"ONNX Runtime","optional":false},{"name":"Platform Engineering","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"Quantization","optional":false},{"name":"Ray","optional":false},{"name":"Ray Serve","optional":false},{"name":"RunPod","optional":false},{"name":"Seldon Core","optional":false},{"name":"TensorRT-LLM","optional":false},{"name":"TorchServe","optional":false},{"name":"Triton","optional":false},{"name":"vLLM","optional":false},{"name":"Accelerate","optional":true},{"name":"NCCL","optional":true},{"name":"TensorRT","optional":true}],"status":"closed","first_seen_at":"2026-04-24T19:14:58Z","employer_posted_date":"2026-04-24","last_verified_at":"2026-10-06T02:23:43Z","board_verified":false,"closed_at":"2026-10-06T02:23:43Z","days_open":164,"trust":{"level":"stale","repost_count":0,"flags":["stale"],"days_open":163},"description":"SPREEAI is a fast-growing, innovative AI company at the forefront of fashion and e-commerce,revolutionizing how consumers engage with fashion through lifelike photorealistic try-on technology and hyper-personalized shopping experiences.Our mission is to redefine the retail landscape with cutting-edge AI solutions that blend high fashion and technology. We thrive in a dynamic, fast-paced environment where creativity meets technology to drive real impact. If you are passionate about innovation and shaping the future of fashion, SPREEAI offers a platform to make your mark.\n About the Role\nSPREEAI is building the future of AI-powered commerce through photorealistic virtual try-on and multimodal intelligence. We bring together cutting-edge AI and real-world retail to deliver production systems that redefine how people shop online.\nWe are looking for a Principal Engineer to build the infrastructure, deployment pipelines, and observability systems that enable multimodal AI models to move from research prototypes to reliable, production-grade deployments powering real-time virtual try-on experiences for global retail partners.\nThis role spans ML platform engineering, deployment systems, GPU infrastructure, and observability. You will partner closely with Applied Science, AI Platform, Product, and Partner Engineering to enable rapid research iteration and reliable model delivery at scale.\nWhat You'll Own\nML Platform & Training Enablement\nBuild and operate SPREEAI’s end-to-end ML platform spanning training, evaluation, deployment, and monitoring.\nEnable scalable and reliable training workflows through orchestration, infrastructure, and resource management systems.\nDefine platform standards for model packaging, model registry, dataset lineage, experiment tracking, checkpointing, and deployment automation.\nDeployment, Inference & Observability\nEnable reliable and scalable inference deployments through standardized serving, orchestration, and monitoring frameworks.\nBuild and operate model deployment pipelines with versioning, reproducibility, rollback, approval gates, evaluation gates, and production observability.\nEstablish production SLOs for latency, availability, error rate, GPU saturation, cold-start time, cost per inference, and model quality drift.\nStandardize and support serving infrastructure using modern inference runtimes such as vLLM, NVIDIA Triton, TensorRT-LLM, Ray Serve, TorchServe, ONNX Runtime, or equivalent systems.\nGPU Infrastructure & System Efficiency\nDesign and manage GPU allocation, scheduling, and resource utilization across training and inference workloads.\nImprove GPU utilization, throughput, latency, reliability, and cost efficiency across model lifecycle systems.\nDesign and operate model evaluation and benchmarking systems, including automated regression detection and quality gates for production releases.\nPartner with research teams to productionize new capabilities by providing robust infrastructure, tooling, and deployment pathways.\nWhat We're Looking For\n10+ years of software engineering / infrastructure experience, with 5+ years in ML infrastructure, MLOps, distributed systems, or AI platform engineering.\nDeep experience with Python, PyTorch, Kubernetes, Docker, cloud infrastructure, and GPU-based workloads.\nStrong understanding of distributed systems and large-scale ML infrastructure design.\nExperience with ML workflow orchestration systems such as Ray, Kubeflow, Argo, Airflow, Flyte, or Metaflow.\nExperience deploying and managing production inference systems using platforms like Triton, vLLM, TensorRT-LLM, Ray Serve, KServe, Seldon, BentoML, TorchServe, or custom services.\nStrong understanding of inference optimization techniques such as batching, quantization, CUDA graphs, and memory-aware scheduling.\nExperience with model registries, experiment tracking, CI/CD for ML, canary deployments, shadow traffic, rollback strategies, and production monitoring.\nStrong cloud experience across AWS, GCP, Azure, or GPU-focused providers like CoreWeave, Lambda Labs, or RunPod.\nAbility to debug performance bottlenecks across distributed systems, containers, networking, GPU memory, and storage layers.\nStrong ownership mindset with the ability to define architecture, set platform standards, and drive execution across teams.\nNice to Have\nExperience with multimodal, vision, or generative AI systems.\nExperience with large-scale GPU clusters e.g. A100/H100, NCCL, and high-throughput data pipelines.\nExperience designing evaluation and monitoring systems for generative AI workloads.\nFamiliarity with ML security, privacy, and data governance practices.\nExperience building internal developer platforms for research teams.\nSuccess Looks Like\nWithin 6 months, you will:\nCreate reliable research-to-production pathways for SPREEAI’s core AI models.\nReduce manual model deployment friction through standardized pipelines and tooling.\nImprove GPU utilization and reduce training and inference costs.\nEstablish robust observability and evaluation gates for production model releases.\nAccelerate the delivery of new AI capabilities into partner-facing experiences.\nWhy This Role Matters\nThis is not a traditional DevOps role. This is the infrastructure backbone that enables SPREEAI to turn frontier AI research into reliable, scalable, production-grade systems. You will define the systems powering real-time AI experiences where latency, cost, and model quality directly impact end-user experience.\nWhy Join SPREEAI?\nBuild the Core AI Infrastructure, Not Just Features: You will define how multimodal AI systems are reliably deployed, monitored, and scaled-directly shaping the performance, cost efficiency, and reliability of real-world AI products.\nOwn Systems End-to-End: You will own critical infrastructure decisions across deployment, observability, and resource management, with direct impact on production systems serving real partner traffic.\nWork on Hard, High-Leverage Problems: From GPU efficiency to large-scale deployment systems, you will tackle challenges that sit at the frontier of real-time AI infrastructure.\nHigh Velocity, Low Bureaucracy & Direct Impact: We operate with tight feedback loops between research, platform, and product, enabling rapid iteration and meaningful impact without organizational friction.","description_format":"text","description_chars":6313,"description_truncated":false,"requirements":{"experience_years_min":10,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[{"name":"United States","iso":"US","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Artificial Intelligence","Commerce","Retail & Commerce AI"],"lifecycle":[{"event":"open","at":"2026-09-26T07:20:42Z"},{"event":"close","at":"2026-10-06T02:23:43Z"}],"visa":[{"country":"US","licensed_sponsor":true,"evidence":"H-1B filings in 12 months: 1","filings_12m":1,"filings_prev_12m":1,"green_card_filings_12m":0,"median_offered_wage_usd":387500,"route":null,"cap_exempt":false,"checked_at":"2026-10-03T21:08:04+00:00","sources":["US Department of Labor: LCA disclosure data (H-1B, H-1B1, E-3)"],"filings_for_role_12m":0}],"liveness":null,"pay":null,"html_url":"https://alion.io/job/spreeai-principal-engineer-ai-platform-infrastructure","json_url":"https://alion.io/job/spreeai-principal-engineer-ai-platform-infrastructure.json","meta":{"generated_at":"2026-10-14T08:33:37Z","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":9351,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-15T00:00:00Z"}},"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":1765982},"rest":"https://alion.io/mcp/rest/get_company?id=1765982"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fspreeai-principal-engineer-ai-platform-infrastructure"},{"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%2Fspreeai-principal-engineer-ai-platform-infrastructure"},{"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%2Fspreeai-principal-engineer-ai-platform-infrastructure"},{"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/spreeai-principal-engineer-ai-platform-infrastructure\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fspreeai-principal-engineer-ai-platform-infrastructure"}]}