Senior NLP Engineer LLM

Job description

<p><p></p><p><b>About Company (https : //avisoft.io/) is a Technology and IT services company based in Mohali and Jammu serving clients globally.<br/>We offer Product Engineering, IT Consultancy, Project Outsourcing and Staff Augmentation services.

We partner with businesses to design and build Tech platforms from scratch, or to re-engineer and modernize their legacy systems.<br/><br/><p>Our teams have expertise in Full Stack Technologies, REST API Servers, Blockchain, DevOps, Cloud Technologies, Data Engineering, and Test Automation.

We are building next gen SaaS platforms for e-commerce and health-tech the Role :</b><br/><br/></p><p>We are seeking a highly skilled Senior NLP Engineer with expertise in large language models (LLMs), prompt engineering, and transformer-based architectures.</p><p><br/>The ideal candidate will have strong experience fine-tuning, deploying, and optimizing advanced NLP models for real-world applications such as summarization, text generation, and question answering.</p><p><br/>You will collaborate with cross-functional teams to design scalable, production-ready solutions while addressing challenges such as bias, hallucinations, and knowledge cutoffs.</p><p><br/></p><p><b>Key Responsibilities : </b><br/><br/></p><p>- Fine-tune pre-trained models on domain-specific datasets to optimize for summarization, text generation, question answering, and related tasks.<br/><br/></p><p>- Prompt Engineering : Design, test, and iterate on contextually relevant prompts to guide model outputs for desired performance.<br/><br/></p><p>- Implement and refine instruction-based prompting strategies to achieve contextually accurate results.<br/><br/></p><p>- Apply zero-shot, few-shot, and many-shot learning methods to maximize model performance without extensive retraining.<br/><br/></p><p>- Leverage Chain-of-Thought (CoT) prompting for structured, step-by-step reasoning in complex tasks.<br/><br/></p><p>- Evaluate model performance using BLEU, ROUGE, and other relevant metrics; identify opportunities for improvement.<br/><br/></p><p>- Deploy trained and fine-tuned models into production environments, integrating with real-time systems and pipelines.<br/><br/></p><p>- Identify, monitor, and mitigate issues related to bias, hallucinations, and knowledge cutoffs in LLMs.<br/><br/></p><p>- Work closely with cross-functional teams (data scientists, engineers, product managers) to design scalable and efficient NLP-driven Skills : </b></p><p><br/></p>- 7+ years of overall experience in software/AI development with at least 2+ years in transformer-based NLP models.<br/><br/><p>- 4+ years of hands-on expertise with transformer architectures (GPT, BERT, T5, RoBERTa, etc.</p><br/><br/><p>- Strong understanding of attention mechanisms, self-attention layers, tokenization, embeddings, and context windows.</p><br/><br/><p>- Proven experience in fine-tuning pre-trained models for NLP tasks (summarization, classification, text generation, translation, Q&A).</p><br/><br/>- Expertise in prompt engineering, including zero-shot, few-shot, many-shot learning, and prompt template creation.<br/><p><br/></p><p>- Experience with instruction-based prompting and Chain-of-Thought prompting for reasoning tasks.</p><br/><br/><p>- Proficiency in Python and NLP libraries/frameworks such as Hugging Face Transformers, SpaCy, NLTK, PyTorch, TensorFlow.</p><br/><br/><p>- Strong knowledge of model evaluation metrics (BLEU, ROUGE, perplexity, etc.</p><p><br/></p><p>- Experience in deploying models into production environments.</p><br/><br/><p>- Awareness of bias, hallucinations, and limitations in LLM to Have : </b><br/><br/></p><p>- Experience with LLM observability tools and monitoring pipelines.<br/><br/></p><p>- Exposure to cloud platforms (AWS, GCP, Azure) for scalable model deployment.<br/><br/></p><p>- Knowledge of MLOps practices for model lifecycle Key Skills : </b></p><p><br/></p><p>2+ years in transformer-based NLP, 4+ years with GPT/BERT/T5/RoBERTa, expertise in fine-tuning, prompt engineering (zero/few/many-shot, CoT, instruction-based), strong Python & NLP frameworks (Hugging Face, PyTorch, TensorFlow, SpaCy, NLTK), and proven experience in model evaluation (BLEU, ROUGE, perplexity) & production Type : </b>IT : </b></p><p><br/></p><p>7+ years in software/AI development with 2+ years in transformer-based NLP and 4+ years in hands-on work with GPT, BERT, T5, RoBERTa, and related architectures</p><br/><p></p><br/></p> (ref:hirist.tech)

Required Skill Profession

Computer Occupations