Who we are:

At UST, we help the world’s best organizations grow and succeed through transformation. Bringing together the right talent, tools, and ideas, we work with our client to co-create lasting change. Together, with over 26,000 employees in 25 countries, we build for boundless impact—touching billions of lives in the process. Visit us at .

The Opportunity:

UST is looking for LLM Engineer On-Prem Deployment & Domain Tuning (Semiconductor Focus).

Key Roles & Responsibilities:

LLM Deployment & Tuning: Hands-on experience with deploying open-source LLMs (e.g., LLaMA, Mistral, SemiKong etc) using tools like Ollama, vLLM, or containerized stacks on GPU-based on-prem infrastructure.

Required Skills:

·       RAG Implementation: Strong expertise in building Retrieval-Augmented Generation (RAG) pipelines using vector databases such as FAISS, Qdrant, or Weaviate, integrated with tools like LangChain or LlamaIndex.

·       Model Fine-Tuning: Proficiency in instruction tuning, LoRA/QLoRA, or full fine-tuning using frameworks like HuggingFace Transformers, PEFT, and DeepSpeed. Training

·       Data Creation: Proven experience in collecting, curating, cleaning, and annotating domain-specific datasets, including document chunking, prompt engineering, and formatting data for supervised fine-tuning.

·       Evaluation & Benchmarking: Ability to benchmark multiple LLMs (e.g., SemiKong, Falcon, MPT) and quantify performance on tasks like Q&A, summarization, and domain comprehension.

·       Semiconductor Domain Understanding: Working familiarity with semiconductor industry terminology, documents (e.g., datasheets, specs), or workflows is highly desirable.

·       GPU & Infra Proficiency: Solid understanding of CUDA, PyTorch, model parallelism, and performance optimization on multi-GPU environments. Proficient in Python, Git, and containerization (Docker)

Desired Skills:

·       Experience with Kubernetes or MLOps is a bonus.

Qualification:

·       BTech in Computer Science

·       3 to 6 years of experience in ML/NLP/LLM engineering, including at least 1 to 2 years hands-on with LLMs (deployment, tuning, RAG).

·       Experience building custom LLM/SLM solutions using open-source models, especially in resource-constrained or secure/on-prem environments.

What we believe:

We’re proud to embrace the same values that have shaped UST since the beginning. Since day one, we’ve been building enduring relationships and a culture of integrity. And today, it's those same values that are inspiring us to encourage innovation from everyone, to champion diversity and inclusion and to place people at the center of everything we do. 

Humility:

We will listen, learn, be empathetic and help selflessly in our interactions with everyone.

Humanity:

Through business, we will better the lives of those less fortunate than ourselves.

Integrity:

We honor our commitments and act with responsibility in all our relationships.

Equal Employment Opportunity Statement

UST is an Equal Opportunity Employer. We believe that no one should be discriminated against because of their differences, such as age, disability, ethnicity, gender, gender identity and expression, religion or sexual orientation.

All employment decisions shall be made without regard to age, race, creed, color, religion, sex, national origin, ancestry, disability status, veteran status, sexual orientation, gender identity or expression, genetic information, marital status, citizenship status or any other basis as protected by federal, state, or local law.

UST reserves the right to periodically redefine your roles and responsibilities based on the requirements of the organization and/or your performance.

• To support and promote the values of UST.

• Comply with all Company policies and procedures