Expert Inference Architect

4 days ago


Hyderabad City Taluka, Pakistan beBeeInference Full time $180,000 - $300,000
Cloud Computing Professional

Transform Your Career in Cloud Computing

Are you looking for a challenging opportunity to drive innovation and simplicity in cloud computing? Do you thrive in fast-paced environments and have a passion for making a difference?

About the Role:

  • Design and implement distributed inference platforms for optimized model serving.
  • Optimize runtime and infrastructure layers for best model performance.
  • Develop novel techniques for serving custom models and scale the platform globally.
  • Contribute to open source inference engines to improve their performance on DigitalOcean cloud.
  • Build tooling and observability for system health monitoring and auto-tuning capabilities.
  • Develop benchmarking frameworks for model serving performance testing.
  • Mentor engineers on inference systems, GPU infrastructure, and distributed inference best practices.

Requirements:

  • Bachelor's or Master's degree in Computer Science, Electrical Engineering, or related field.
  • Experience building distributed systems with Kubernetes, gRPC, Go, Python.
  • Experience with GPU programming using CUDA, ROCm.
  • Knowledge of L3-L7 network protocols, block storage, object storage.
  • Proven track record defining and achieving performance KPIs (latency, throughput, cost).

Preferred Qualifications:

  • Experience with one or more inference engines: vLLM, SGLang, Modular.
  • Familiarity with one or more distributed inference serving frameworks - llm-d, NVIDIA dynamo, Ray Serve.
  • Knowledge of distributed inference optimization techniques - tensor/data parallelism, KV cache optimizations, smart routing.
  • Familiarity with common LLM architectures and inference optimization techniques.
  • Experience with GPU Interconnect technologies like NVlink, XGMI, RoCE.
  • Open source contributions to inference libraries, frameworks, model kernels.


  • Hyderabad City Taluka, Pakistan beBeeAI Full time $180,000 - $220,000

    Job DescriptionThe Senior Staff, AI Solutions Architect will occupy a vital position focusing on architecting and realizing value of the comprehensive AI feature set within ServiceNow. Based in Hyderabad, this role reports directly to the Sr. Dir, Platform Architecture.As a pivotal figure in the AI Solutions team, the Senior Staff, AI Solutions Architect...

  • AWS Cloud Architect

    1 week ago


    Hyderabad City Taluka, Pakistan Hitachi Digital Services Full time

    Join to apply for the AWS Cloud Architect role at Hitachi Digital ServicesContinue with Google Continue with GoogleJoin to apply for the AWS Cloud Architect role at Hitachi Digital ServicesGet AI-powered advice on this job and more exclusive features.Sign in to access AI-powered advicesContinue with Google Continue with GoogleContinue with Google Continue...

  • Principal Architect

    4 weeks ago


    Hyderabad City Taluka, Pakistan JP Morgan Chase Full time

    Step into the future with us as an Innovation and Incubation Architect at Cloud Foundation Services, where you'll be at the forefront of driving groundbreaking technical efforts that fuel our research, development, and innovation initiatives.As a Principal Architect at JPMorgan Chase within the Enterprise Technology, youprovide expertise to enhance and...

  • Data Architect

    4 weeks ago


    Hyderabad City Taluka, Pakistan GSPANN Technologies, Inc Full time

    Data Architect, ETL, Data Engineer, Python, SQLDescriptionGSPANN is hiring a Data Architect for their data platform. As we march ahead on a tremendous growth trajectory, we seek passionate and talented professionals to join our growing family.Location: Gurugram / Hyderabad / PuneRole Type: Full TimePublished On: 26 September 2024Experience: 8+ YearsShare...

  • Tech Lead

    3 weeks ago


    Hyderabad City Taluka, Pakistan Gramener Full time

    Join to apply for the Tech Lead / Architect – Python, Gen AI role at Gramener3 weeks ago Be among the first 25 applicantsJoin to apply for the Tech Lead / Architect – Python, Gen AI role at GramenerGet AI-powered advice on this job and more exclusive features.Work Location: Hyderabad / Bangalore / NoidaWhat Gramener offers youGramener will offer you an...


  • Hyderabad City Taluka, Pakistan beBeeTechlead Full time $180,000 - $220,000

    Job TitleAmbitious Tech Leader Wanted to Drive AI InnovationAbout the RoleWe are seeking a highly experienced Tech Lead to spearhead the architecture and delivery of modern, scalable data applications powered by Generative AI.This role focuses on solution design, architectural leadership, and cross-functional collaboration across AI/ML platforms, backend...

  • Principal Architect

    2 weeks ago


    Hyderabad City Taluka, Pakistan JP Morgan Chase Full time

    Step into the role of a Principal Architect at JP Morgan Chase and become a driving force behind the development and adoption of cutting-edge, cloud-based technologies.As a Principal Architect at JPMorgan Chase within the Global Customer Platform unit, you will provide expertise to enhance and develop architecture platforms utilizing modern cloud-based...


  • Hyderabad City Taluka, Pakistan Warner Bros. Discovery, Inc. Full time

    Welcome to Warner Bros. Discovery… the stuff dreams are made of.Who We Are…When we say, "the stuff dreams are made of," we're not just referring to the world of wizards, dragons and superheroes, or even to the wonders of Planet Earth. Behind WBD's vast portfolio of iconic content and beloved brands, are the storytellers bringing our characters to life,...


  • Hyderabad City Taluka, Pakistan beBeeMachineLearning Full time $180,000 - $250,000

    Senior AI/ML Operations EngineerThis role involves designing, building, and deploying scalable Artificial Intelligence for IT Operations (AIOps) and Machine Learning Operations (MLOps) frameworks. The ideal candidate will have expert-level coding skills in Python and Bash, with a strong understanding of DevOps, MLOps, or AIOps.Key Responsibilities:Architect...


  • Hyderabad City Taluka, Pakistan Rojgar Group Full time

    Full TimeFull TimeGurgaon, Hyderabad & PunePosted 10 months ago4500000 INR / YearSalary: 4500000Job Description And ExperienceJob Role: Solution Architect:Experience: 10+ YearsRelevant Exp: 3yr/Preferred – 5yrLocation: Gurgaon/Pune/HyderabadGeneral Shift: APAC region but ready for meetings/calls in extended hoursProject Lead exp. requiredRole OverviewWe...