Baseten
Baseten
Baseten उन कंपनियों के लिए मॉडल इन्फरेंस इंफ्रास्ट्रक्चर उपलब्ध कराता है, जो मशीन लर्निंग और एआई एप्लिकेशन तैनात करती हैं। इसका प्लेटफ़ॉर्म तेज़ और बड़े पैमाने पर मॉडल सर्विंग के लिए बनाया गया है, जिसमें उच्च-थ्रूपुट इन्फरेंस, तेज़ परिनियोजन, ऑटोस्केलिंग, सुरक्षित एंटरप्राइज़ मॉडल सर्विंग और ओपन-सोर्स मॉडल पैकेजिंग का समर्थन शामिल है। Baseten इंजीनियरिंग और मशीन लर्निंग टीमों को मॉडल इंफ्रास्ट्रक्चर की परिचालन संबंधी चुनौतियों को संभालने में मदद करता है, ताकि वे डोमेन-विशिष्ट मॉडल विकसित करने पर ध्यान केंद्रित कर सकें। कंपनी कृत्रिम बुद्धिमत्ता, SaaS और एंटरप्राइज़ तकनीक के क्षेत्रों में काम करती है और इसमें 11–50 कर्मचारी हैं।

Inference Performance Software Engineer at Baseten (Hybrid)

Baseten is hiring an inference performance engineer to optimize LLM runtimes, GPU kernels, and model-serving systems. The role focuses on improving production inference speed, hardware utilization, and cost efficiency.

विवरण

  • Productionize advanced inference methods such as quantization, speculative decoding, KV-cache reuse, chunked prefill, LoRA, guided generation, and custom scheduling or routing.
  • Analyze the full inference pipeline, optimizing kernel overhead, memory placement, request scheduling, prefill/decode separation, and cache-aware routing.
  • Increase tokens per GPU-hour and utilization while balancing latency, throughput, and cost.
  • Deploy and optimize emerging model architectures on new hardware platforms.
  • Create benchmarks spanning model types, batch sizes, sequence lengths, and hardware setups.
  • Submit improvements to open-source inference projects including vLLM, SGLang, and TensorRT-LLM.
  • Work with model, infrastructure, and customer-facing teams to deliver measurable performance gains.

आवश्यकताएँ

  • Degree at the bachelor's, master's, or doctoral level in computer science, engineering, mathematics, or a related discipline.
  • Professional experience with at least one general-purpose programming language, including Python or C++.
  • Working knowledge of LLM optimization methods such as quantization, speculative decoding, and continuous batching.
  • Strong command of machine-learning libraries, particularly PyTorch, TensorRT, or TensorRT-LLM.
  • Demonstrated interest in and practical experience with large language models.
  • Thorough understanding of GPU architecture.

लाभ

  • Competitive pay package with meaningful equity participation.
  • For U.S. employees, full medical, dental, and vision insurance coverage extends to employees and their dependents.
  • Flexible paid time off, plus a company-wide winter break.
  • Paid parental leave.
  • Fertility and family-building support through a Carrot stipend.
  • For U.S. employees, a company-facilitated 401(k) plan.
  • Opportunities to work with a range of machine-learning startups, supporting substantial learning and professional networking.

संबंधित नौकरियाँ

coni+partner AG

Quantitative Finance Specialist, UCITS and AIF

coni+partner AG

Oversee fund performance measurement, attribution, and risk analysis for UCITS and AIF portfolios. Support client reporting, benchmark management, operational controls, and technology projects in Swiss financial services.

खोलें
Nestle

Senior Finance Analyst, Capital Project Cost Controller

Nestle

Senior finance analyst overseeing capital project budgets for Nestlé Purina North America. The role covers cost forecasting, construction spend assurance, and financial governance.

खोलें
Harpak-ULMA Packaging

Remote Field Service Technician – Nevada | Harpak-ULMA Packaging

Harpak-ULMA Packaging

Install, troubleshoot, and repair Harpak-ULMA packaging equipment, with a focus on multi-head weighers. Provide customer support across a territory requiring 70–85% travel.

खोलें
Qualus

Relay Field Technician I

Qualus

Test and calibrate substation protection, control, and communications systems. Support field engineering work for Qualus power infrastructure clients.

खोलें
DATAGROUP

On-Site IT Service Engineer

DATAGROUP
1,001 – 5,000 कर्मचारी
SaaSपरामर्शविपणन

Provide on-site workplace and meeting-room IT support for DATAGROUP customers. Install, repair, and maintain PCs, network equipment, telecommunications, and specialist devices.

खोलें
InTTrust S.A.

Data Analyst, SQL and Oracle Analytics Cloud

InTTrust S.A.

InTTrust is hiring a Data Analyst in Greece to work with SQL, Oracle Analytics Cloud, and machine learning. The role focuses on dashboards, semantic models, and turning data into practical business insights.

खोलें
AtkinsRéalis

Senior Project Planning and Controls Engineer – AtkinsRéalis, Gurugram

AtkinsRéalis

Lead planning and project controls across AtkinsRéalis infrastructure and EPC projects, managing schedules, costs, risks, and performance reporting. Build Power BI insights and support delivery teams working across global projects.

खोलें
ICT Digital Solutions GmbH
WEX
IQ Plus AG

Software Architect, Microservices

IQ Plus AG
51 – 200 कर्मचारी
B2BSaaSभर्ती

Lead the architecture of new tax solutions built on microservices. Set development standards, coordinate technical improvements, and work with product, engineering, business analysis, and customers.

खोलें