Inference Optimization Engineer(LLM and Runtime)

Role Overview: You are a highly skilled and innovative Inference Optimization (LLM and Runtime) at Sustainability Economics.ai, responsible for designing, developing, and optimizing cutting-edge AI systems. Your role involves integrating AI-driven cloud solutions with sustainable energy to create scalable, intelligent ecosystems that drive efficiency and innovation across industries. Collaborating with cross-functional teams, you will build production-ready AI solutions that address real-world business challenges and keep the platforms at the forefront of AI innovation. Key Responsibility: - Optimization and customization of large-scale generative models (LLMs) for efficient inference and serving. - Applying and evaluating advanced model optimization techniques such as quantization, pruning, distillation, tensor parallelism, caching strategies, etc., to enhance model efficiency, throughput, and inference performance. - Implementing custom fine-tuning pipelines using parameter-efficient methods (LoRA, QLoRA, adapters etc.) to achieve task-specific goals while minimizing compute overhead. - Optimizing runtime performance of inference stacks using frameworks like vLLM, TensorRT-LLM, DeepSpeed-Inference, and Hugging Face Accelerate. - Designing and implementing scalable model-serving architectures on GPU clusters and cloud infrastructure (AWS, GCP, or Azure). - Working closely with platform and infrastructure teams to reduce latency, memory footprint, and cost-per-token during production inference. - Evaluating hardwaresoftware co-optimization strategies across GPUs (NVIDIA A100/H100), TPUs, or custom accelerators. - Monitoring and profiling performance using tools such as Nsight, PyTorch Profiler, and Triton Metrics to drive continuous improvement. Qualification Required: - Ph.D. in Computer Science or a related field, with a specialization in Deep Learning, Generative AI, or Artificial Intelligence and Machine Learning (AI/ML). - 2-3 years of hands-on experience in large language model (LLM) or deep learning optimization, gained through academic or industry work. Additional Company Details: Sustainability Economics.ai is a global organization pioneering the convergence of clean energy and AI. Guided by exceptional leaders, the company is committed to making long-term efforts to fulfill its vision through technical innovation, client services, expertise, and capability expansion. Joining the team at Sustainability Economics.ai offers you the opportunity to shape a first-of-its-kind AI + clean energy platform, work with a mission-driven team obsessed with impact, and leave your mark at the intersection of AI and sustainability.,