Edge LLM Engineer
About The Client:
Client is a Japanese multinational conglomerate specializing in power systems, social infrastructure, electronic devices, digital solutions, and more, with a diverse product range including medical equipment, semiconductors, and industrial systems. Founded in 1875 and formally incorporated in 1939, Toshiba has evolved from its origins in electronics and electrical manufacturing to become a global leader in innovative technology and systems across numerous sectors.
About The Job:
- We are looking for an engineer experienced in deploying and optimizing Large Language Models on edge devices, preferably NVIDIA Jetson platforms.
- The role is not limited to model inference; the candidate should be able to design practical LLM-based solutions for real-world scenarios using prompt engineering, input preprocessing, caching strategies, data creation, and model fine-tuning when required.
- The ideal candidate should understand how to make LLM applications reliable, efficient, and context-aware under edge-device constraints such as limited compute, memory, latency, and power.
Qualifications:
Mandatory Skills
- Hands-on experience with LLMs, prompt engineering, and scenario-specific prompt design.
- Experience running AI/ML models on edge devices with compute and memory constraints.
- Practical knowledge of preprocessing techniques for text, speech transcripts, and structured inputs.
- Experience implementing caching, context management, and optimization techniques for LLM applications.
- Ability to create datasets and fine-tune or adapt models for domain-specific use cases.
- Strong Python programming skills.
- Understanding of NLP tasks such as intent handling, entity extraction, and text classification.
- Experience with model evaluation, latency optimization, and debugging AI behavior.
- Familiarity with NVIDIA Jetson or similar edge AI platforms.
- Experience with speech processing, speech-to-text systems, and audio preprocessing.
- Knowledge of noise handling, speech enhancement, and robust voice input pipelines.
- Experience with NER models and entity extraction pipelines.
- Familiarity with TensorRT, ONNX, PyTorch, Hugging Face, or similar model deployment tools.
- Experience with quantization, pruning, distillation, or other model compression techniques.
- Knowledge of retrieval-augmented generation, vector databases, or local knowledge caching.
- Experience building real-time AI applications on embedded Linux systems.
- Familiarity with multilingual or domain-specific language processing.
- Experience integrating LLMs with sensors, robotics, industrial systems, or IoT devices.
How to Apply: Interested candidates are encouraged to respond/submit their updated resumes, and for additional job opportunities, please visit Jobs In India – VARITE.
Unlock Rewards: Refer Candidates and Earn.
If you're not available or interested in this opportunity, please pass this along to anyone in your network who might be a good fit and interested in our open positions. VARITE offers a Candidate Referral program, where you'll receive a one-time referral bonus based on the following scale if the preferred candidate completes a three-month assignment with VARITE.
Experience Level Bonus Referral:
| 0-2 years | INR 5,000 |
| 2-6 years | INR 7,500 |
| 6+ years | INR 10,000 |
About VARITE: VARITE is a global staffing and IT consulting company providing technical consulting and team augmentation services to Fortune 500 Companies in USA, UK, CANADA and INDIA. VARITE is currently a primary and direct vendor to the leading corporations in the verticals of Networking, Cloud Infrastructure, Hardware and Software, Digital Marketing and Media Solutions, Clinical Diagnostics, Utilities, Gaming and Entertainment, and Financial Services.
Equal Opportunity Employer:
VARITE is an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees. We do not discriminate based on race, color, religion, sex, sexual orientation, gender identity or expression, national origin, age, marital status, veteran status, or disability status.
