Hiring: Edge LLM Engineer – to work on NVIDIA Jetson & Edge Devices - 3 months Project

Hybrid 3 days from office (Bangalore) Experience: 3–8 Years (Flexible based on expertise) About the Role: We are looking for a Edge LLM Engineer to design, deploy, and optimize Large Language Model (LLM) solutions on edge devices, preferably NVIDIA Jetson platforms. This role goes beyond model inference and requires the ability to build practical, production-ready AI applications that operate efficiently under real-world edge constraints. The ideal candidate should have strong expertise in prompt engineering, input preprocessing, caching strategies, dataset creation, model adaptation, and performance optimization. You will be responsible for developing reliable, context-aware, and low-latency AI solutions that can run effectively on devices with limited compute, memory, and power resources. Key Responsibilities: 1. Design and deploy LLM-powered applications for edge environments. 2. Develop effective prompt engineering strategies tailored to specific use cases. 3. Implement preprocessing pipelines for text, speech transcripts, and structured data. 4. Build caching, context management, and memory optimization mechanisms for efficient inference. 5. Create, curate, and enhance datasets for domain-specific AI applications. 6. Fine-tune, adapt, or optimize models when required to improve performance and accuracy. 7. Evaluate model quality, latency, reliability, and resource utilization. 8. Debug and improve AI behaviour in production environments. 9. Collaborate with cross-functional teams to deliver end-to-end AI solutions. 10. Optimize applications for low-latency and resource-constrained edge devices. Mandatory Skills 1. Hands-on experience with Large Language Models (LLMs), prompt engineering, and scenario-specific prompt design. 2. Experience deploying AI/ML models on edge devices with compute and memory constraints. 3. Strong understanding of text, speech transcript, and structured data preprocessing techniques. 4. Experience implementing caching, context management, and optimization strategies for LLM applications. 5. Ability to create datasets and fine-tune/adapt models for domain-specific requirements. 6. Strong Python programming skills. 7. Understanding of NLP tasks such as intent recognition, entity extraction, and text classification. 8. Experience with model evaluation, latency optimization, and AI behavior debugging. 9. Familiarity with NVIDIA Jetson platforms or similar edge AI hardware. Good to Have 1. Experience with speech processing, speech-to-text systems, and audio preprocessing. 2. Knowledge of noise reduction, speech enhancement, and robust voice-input pipelines. 3. Experience building NER and entity extraction solutions. 4. Familiarity with TensorRT, ONNX, PyTorch, Hugging Face, and related deployment frameworks.