We are looking
for a Senior Software Engineer to develop and optimize deep learning models,
including CNNs, LLMs, and MoE, for efficient inference across CPU, GPU,
hardware accelerators, and edge devices. The role focuses on quantization,
model compression, high-performance kernel implementation, transformer
optimization, and production deployment.
Responsibilities:
• Develop and optimize deep learning models (CNNs,
LLMs, MoE) for efficient inference across CPU, GPU, hardware accelerators, and
edge devices.
• Design and implement quantization algorithms
(PTQ, QAT, GPTQ, AWQ) from scratch.
• Apply model compression techniques such as
pruning, decomposition, and distillation.
• Implement and optimize quantized kernels (INT8,
INT4, FP8) using C++ for high performance.
• Translate research papers into production-ready
implementations.
• Optimize latency, throughput, and memory usage
for real-world deployment.
• Work on transformer optimization including
KV-cache, PEFT (LoRA/QLoRA), and MoE models.
• Profile, benchmark, and debug model performance
across different hardware platforms.
Requirements
Education:
• 4+ years of relevant experience.
• Strong programming skills in Python and C++.
• Proven experience in quantization algorithms
(PTQ, QAT, GPTQ, AWQ).
• Hands-on experience in pruning, model
compression, and inference optimization.
• Experience implementing quantization or
optimization techniques from scratch.
• Strong understanding of CNNs, Transformers, and
LLM architectures.
• Experience with PyTorch / ONNX and model
deployment pipelines.
• Strong problem-solving and performance
optimization skills.
Need to have (Can be bridged):
No
additional bridged skills were specified.
Good to have (Not essential):
• Experience with MoE architectures and PEFT
techniques (LoRA, QLoRA).
• Knowledge of TensorRT, ONNX Runtime, TVM, and
MLIR.
• Familiarity with hardware-aware optimization
across GPU, NPU, and edge devices.
• Experience in research paper implementation or
open-source contributions.
Preferred Qualifications (Optional):
No
additional preferred qualifications were specified.
Skills Required
- BE, BTech, MS, or MTech in Computer Science or a related field
- 4 or more years of professional experience
- Strong programming skills in Python and C++
- Proven experience with PTQ, QAT, GPTQ, and AWQ quantization algorithms
- Hands-on experience with pruning, model compression, and inference optimization
- Experience implementing quantization or optimization techniques from scratch
- Strong understanding of CNN, Transformer, and LLM architectures
- Experience with PyTorch, ONNX, and model deployment pipelines
- Strong problem-solving and performance optimization skills
- Experience with MoE architectures and PEFT techniques such as LoRA and QLoRA
- Knowledge of TensorRT, ONNX Runtime, TVM, and MLIR
- Familiarity with hardware-aware optimization for GPUs, NPUs, and edge devices
- Experience implementing research papers or contributing to open source
What We Do
MulticoreWare delivers software IP Solutions and Engineering Services serving a wide group of customers with Compilers & Toolchains, Libraries for SDK, Video codec and AI analytics solutions using various vision & non-vision (Radar, LiDAR, IMU, GPS, etc.) sensors on various heterogenous computing platforms. Our solutions are used in Automotive (ADAS/AD), Surveillance, Defence, Medical Imaging, IoT, Retail, Logistics, Industrial, Robotics, Smart City. MulticoreWare’s industry-leading video codec products (x266™/x265/Ultraziq) have been deployed in live streaming or VOD services across many broadcast customers. FOLLOW US ON SOCIAL MEDIA Youtube: https://www.youtube.com/channel/Multicoreware Twitter: https://twitter.com/MulticoreWare Facebook: https://www.facebook.com/multicoreware Instagram: https://www.instagram.com/multicoreware.inc/
