- Model Inference: Focus on inference optimization to ensure rapid response times and efficient resource utilization during real-time model interactions.
- Hardware Optimization: Run models on various hardware platforms, from high-performance GPUs to edge devices, ensuring optimal compatibility and performance.
- Experimentation and Testing: Regularly run experiments, analyze outcomes, and refine the strategies to achieve peak performance in varying deployment scenarios.
- Staying up to date with the current literature on MLSys
- You care about making something people want. You want to ship something that will bring value to our users. You want to deliver AI solutions end-to-end and not finish building a prototype.
- Bachelor's degree or higher in computer science or a related field.
- You understand how multimodal transformers work.
- You understand the characteristics of LLM inference (KV caching, flash attention, and model parallelization).
- You have experience in system design and optimization, particularly within AI or deep learning contexts.
- You are proficient in Python and have deep understanding of deep learning frameworks such as PyTorch.
- A deep understanding of the challenges associated with scaling AI models for large user bases.
- Previous experience in a high-growth tech environment or a role focused on scaling AI solutions.
- Hands-on experience with large language models or other complex AI architectures.
- Expertise with CUDA and Triton programming and GPU optimization for neural network inference.
- Experience with Rust.
- Experience in adapting AI models to suit a range of hardware, including different accelerators.
- Experience in model quantization, pruning, and other neural network optimization methodologies.
- A track record of contributions to open-source projects (please provide links).
- Some Twitter presence discussing ML Sys topics.
- Become part of an AI revolution
- 30 Days of paid vacation
- Flexible working hours
- Join a dynamic start-up and a rapidly growing team
- Work with international industry and science experts
- Take on responsibility and shape our company and technology
- Regular team events
-
Statutory Accountant
vor 3 Wochen
Archer Daniels Midland Company Heidelberg, DeutschlandHeidelberg · Germany · Finance, Accounting, Audit · - You support the preparation of financial statements of German holding companies and operating units, including the coordination and planning of the financial statement audit process with other members of the accounting teams a ...
-
Head of Core Facility tumor Models
vor 2 Wochen
Deutsches Krebsforschungszentrum Heidelberg, Deutschland**Position**:Head of Core Facility "Tumor Models"** · **Department**: Core Facility "Tumor Models" · **Code number**: · The German Cancer Research Center is the largest biomedical research institution in Germany. With more than 3,000 employees, we operate an extensive scientific ...
-
Platform Leader
vor 2 Wochen
Springer Nature Heidelberg, Deutschland**Platform Leader - Genome editing in preclinical disease models**: · - Employer- Medizinische Fakultät Heidelberg der Universität Heidelberg- Location- Heidelberg, Baden-Württemberg (DE)- Salary- Closing date- 9 Apr 2024- Discipline · Applied Science, Health Science, Life Scienc ...
-
Data Scientist Predictive Maintenance
vor 3 Wochen
Heidelberg Materials AG Heidelberg, DeutschlandIn our mission to become the first industrial tech company in the sector, we decided to bundle Data Analytics, Data Science, AI and Hyperautomation (RPA) · within our new team "Data & Insights". We build a rock-solid foundation by putting in place the processes, organizational st ...
-
Data Scientist Predictive Maintenance
vor 3 Wochen
Heidelberg Materials AG Heidelberg, Deutschland**Job description**: · **Professional** · Entry level · **Heidelberg, Germany** · Location · **Full time** · Contract · **IT/Digital Transformation** · Category · **Any Questions?**: · Florence Rueckle · - Talent Acqusition Expert- · **Data Scientist Predictive Maintenance (f/m/d ...
-
Enterprise Architect
vor 1 Woche
Heidelberg Materials AG Heidelberg, DeutschlandDigital plays a central part in shaping and enabling this new digitization strategy. As part of the Digital EA Team you will play a vital role in shaping the architecture. · As (Senior) Enterprise Architect (f/m/d) it will be your goal to influence leaders (e.g. product owner) an ...
-
Epidemiologist / Postdoc
vor 2 Wochen
Deutsches Krebsforschungszentrum Heidelberg, Deutschland**Position**:Epidemiologist / Postdoc** · **Department**: Cancer Epidemiology · **Code number**: · The German Cancer Research Center is the largest biomedical research institution in Germany. With more than 3,000 employees, we operate an extensive scientific program in the field ...
-
Deutsches Krebsforschungszentrum Heidelberg, Deutschland**Position**:Postdoc in Ontology Engineering for Cancer Research** · **Department**: Radiooncology / Radiobiology · **Code number**: · The German Cancer Research Center is the largest biomedical research institution in Germany. With more than 3,000 employees, we operate an exten ...
-
Several Interdisciplinary Phd Positions
vor 2 Wochen
Universität Heidelberg Heidelberg, DeutschlandThe Heidelberg Graduate School of Mathematical and Computational Methods for the Sciences ( HGS MathComp ) at Heidelberg University is the leading graduate school in Germany that focuses on the complex topic of Scientific Computing. Located in a vibrant research environment, the ...
-
Applications Specialist Nir Spectroscopy
vor 3 Wochen
BÜCHI Labortechnik Heidelberg, Deutschland**Heidelberg, Germany**Applications Specialist NIR Spectroscopy** · Your primary task is to provide support to the market organizations, distribution partners and end-customers including pre · - Type**:Full-time** · **What makes your everyday life exciting?** · - Provide pre · - ...
-
Tax Reporting Expert
vor 3 Wochen
Heidelberg Materials AG Heidelberg, DeutschlandHeidelberg Materials is one of the largest global building materials companies. With more than 51,000 employees in over 50 countries, we are known for our expertise and superior quality. Our headquarters in Heidelberg alone employs over 1,100 people from all over the world, creat ...
-
Group Leader As Platform Leader
vor 3 Wochen
Universitätsklinikum Heidelberg Heidelberg, Deutschlandwanted at the** next possible time** at **Department of General Pharmacology.** · - The research and tasks of the platform include: · - Development and optimization of genome editing procedures: The group works on developing new technologies and methods for precise genome editing ...
-
HR Product Owner Workday
vor 3 Wochen
Heidelberg Materials AG Heidelberg, Deutschland**Job description**: · **Professional** · Entry level · **Heidelberg, Germany** · Location · **Full time** · Contract · **Human Resources** · Category · **Any Questions?**: · Anja Hildenbrand · - Head of HR Advisory & Services- · **HR Product Owner Workday (f/m/d)**: · - For our ...
-
Product Lifecycle Management Lead
vor 2 Wochen
Heidelberg Engineering GmbH` Heidelberg, Deutschland**Fakten**: · - **Standort**: Heidelberg · - **Art der Beschäftigung**: Vollzeit · **Job-ID**: · HE2303_003 · **Wir suchen**: · The Product Lifecycle Management Lead is driving the strategic process of managing the complete journey of our product portfolio from discovery, ideatio ...
-
Working Student
vor 1 Woche
Heidelberg Materials AG Heidelberg, DeutschlandWithin our headquarters in Heidelberg, the Global Competence Center Cement is looking for a Working Student (f/m/d) on a weekly 20-hour basis. You will assist in development and deployment of digital learning elements and related tasks. · **Your next challenge**: · - Conceptualiz ...
-
Student Research Assistant
vor 3 Wochen
Universität Heidelberg Heidelberg, DeutschlandThe Climate-Sensitive Infectious Diseases Lab at the Interdisciplinary Center for Scientific Computing (IWR) offers a position as: · **Student research assistant: Climate data analyst (f/m/d)** · Support one or several of the ongoing projects: · - Data extraction from existing da ...
-
Working Student
vor 3 Wochen
ХайдельбергЦемент Heidelberg, DeutschlandThe department Reporting & Benchmark Analysis at our Competence Center Cement is looking for a Working student (f/m/d). · **Your next challenge**: · - Administrative assistance for the global reporting system on SAP BI platform (roles, authorizations, period settings, plant setti ...
-
Working Student
vor 3 Wochen
Heidelberg Materials AG Heidelberg, DeutschlandThe department Data & Insights at our headquarters in Heidelberg is looking for a Working student (f/m/d) for up to 20 hours per week. · **Your next challenge**: · - Support Team Manager to collect and align on requirements from stakeholders and the team · - Contribute to product ...
-
Senior Geologist
vor 2 Wochen
Heidelberg Materials AG Heidelberg, DeutschlandThe Heidelberg Competence Centers Cement (CCCs) are responsible for the deposit consultancy and Inventory of all HM raw material deposits in the BL Cement. · For our global Competence Center Cement (CCC) we are looking for a Senior Geologist (f/m/d) for deposit management in the ...
-
Regulatory Specialist
vor 1 Woche
Archer Daniels Midland Company Heidelberg, DeutschlandHeidelberg · Germany · Legal, Compliance, Regulatory Affairs, Corporate Security · **Regulatory Specialist - fixed-term (M/F/d)** · **Location : Heidelberg/Germany** · **Your role**: · - Evaluation of raw materials and products for the food and beverage industry in consideration ...
AI Inference Engineer: Large Language Models - Heidelberg, Deutschland - Aleph Alpha GmbH
Beschreibung
Overview
You will join our product team in a position that sits at the intersection of artificial intelligence research and real-world solutions. We foster a highly collaborative work culture where you can expect to work closely with your teammates and have a high level of communication between teams through methodologies such as pair or mob programming.
Your responsibilities
Your profile
What you can expect from us
About us
Aleph Alpha was founded in 2019 with the mission to research and build the foundational technology for an era of strong AI. The team of international scientists, engineers, and innovators researches, develops, and deploys transformative AI like large language and multimodal models and runs the fastest European commercial AI cluster. Its generative AI solutions are the only choice for enterprises and governmental institutions seeking to retain independence, secure their data, and build trustworthy solutions.
