Software Engineer

We are seeking a talented Low-Level Software Engineer for a contract position to contribute to an exciting Processing In Memory (PIM) project, focusing on software exploration and performance modeling for large language model (LLM) inference. This is a 100% on-site role in Grenoble, France.

Key Responsibilities:

• Explore the use of emerging PIM technology to accelerate large language model (LLM) inference.
• Conduct advanced research targeting next-generation edge devices and inference acceleration boards.
• Collaborate with an R&D team at a cutting-edge research institute, driving innovation in system technologies to enhance product competitiveness.
• Core work areas include:
  • Deep analysis of LLM with a focus on the decode phase and KV cache.
  • Profiling performance on innovative inference accelerators.
  • Optimizing LLM execution on PIM-based inference accelerators.
  • Facilitating interactions between NPU and Host CPU.
• Focus on application areas such as LLM inference acceleration for edge devices and servers.

What We’re Looking For:

• 3+ years of experience as a software engineer.
• Expertise in performance profiling and low-level libraries/drivers.
• Proficiency in C/C++ and Python for modeling and performance profiling.
• Knowledge of LLM inference is a plus.
• A demonstrated ability to quickly learn and master new technologies.
• Proven experience in innovative problem-solving and effective communication within a global team environment.