Inference Optimization Engineer(LLM and Runtime)

Location: Bengaluru, Karnataka    About the Company:    Sustainability Economics.ai is a global organization, pioneering the convergence of clean energy and AI, enabling profitable energy transitions while powering end-to-end AI infrastructure. By integrating AI-driven cloud solutions with sustainable energy, we create scalable, intelligent ecosystems that drive efficiency, innovation, and long-term impact across industries. Guided by exceptional leaders and visionaries with decades of expertise in finance, policy, technology, and innovation, we are committed to making long-term efforts to fulfil this vision through our technical innovation, client services, expertise, and capability expansion.    Role Summary:  We are seeking a highly skilled and innovative Inference Optimization (LLM and Runtime) to design, develop, and optimize cutting-edge AI systems that power intelligent, scalable, and agent-driven workflows. This role blends the frontier of generative AI research with robust engineering, requiring expertise in machine learning, deep learning, and large language models (LLMs) and latest trends going on in the industry. The ideal candidate will collaborate with cross-functional teams to build production-ready AI solutions that address real-world business challenges while keeping our platforms at the forefront of AI innovation.    Key Tasks and Accountability:    Optimization and customization of large-scale generative models (LLMs) for efficient inference and serving.  Apply and evaluate advanced model optimization techniques such as quantization, pruning, distillation, tensor parallelism, caching strategies, etc., to enhance model efficiency, throughput, and inference performance.  Implement custom fine-tuning pipelines using parameter-efficient methods (LoRA, QLoRA, adapters etc.) to achieve task-specific goals while minimizing compute overhead.  Optimize runtime performance of inference stacks using frameworks like vLLM, TensorRT-LLM, DeepSpeed-Inference, and Hugging Face Accelerate.  Design and implement scalable model-serving architectures on GPU clusters and cloud infrastructure (AWS, GCP, or Azure).  Work closely with platform and infrastructure teams to reduce latency, memory footprint, and cost-per-token during production inference.  Evaluate hardware–software co-optimization strategies across GPUs (NVIDIA A100/H100), TPUs, or custom accelerators.  Monitor and profile performance using tools such as Nsight, PyTorch Profiler, and Triton Metrics to drive continuous improvement.   Key Requirements:   Education & Experience   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.   Skills    Strong analytical and mathematical reasoning ability with a focus on measurable performance gains.  Collaborative mindset, with ability to work across research, engineering, and product teams.  Pragmatic problem-solver who values efficiency, reproducibility, and maintainable code over theoretical exploration.  Curiosity-driven attitude — keeps up with emerging model compression and inference technologies.    What You’ll Do   Take ownership of end-to-end optimization lifecycle — from profiling bottlenecks to delivering production-optimized LLMs.  Develop custom inference pipelines capable of high throughput and low latency under real-world traffic.  Build and maintain internal libraries, wrappers, and benchmarking suites for continuous performance evaluation.    What you will bring   Hands-on experience in building, optimizing machine learning or Agentic Systems at scale. A builder’s mindset — bias toward action, comfort with experimentation, and enthusiasm for solving complex, open-ended challenges. Startup DNA → bias to action, comfort with ambiguity, love for fast iteration, and flexible and growth mindset.     Why Join Us    Shape a first-of-its-kind AI + clean energy platform.  Work with a small, mission-driven team obsessed with impact.  An aggressive growth path.  A chance to leave your mark at the intersection of AI and sustainability.