Senior NLP Engineer - LLM

About Company (https : / / avisoft.io / ) is a Technology and IT services company based in Mohali and Jammu serving clients globally.

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.

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 :

We are seeking a highly skilled Senior NLP Engineer with expertise in large language models (LLMs), prompt engineering, and transformer-based architectures.

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.

You will collaborate with cross-functional teams to design scalable, production-ready solutions while addressing challenges such as bias, hallucinations, and knowledge cutoffs.

Key Responsibilities :

• Fine-tune pre-trained models on domain-specific datasets to optimize for summarization, text generation, question answering, and related tasks.
• Prompt Engineering : Design, test, and iterate on contextually relevant prompts to guide model outputs for desired performance.
• Implement and refine instruction-based prompting strategies to achieve contextually accurate results.
• Apply zero-shot, few-shot, and many-shot learning methods to maximize model performance without extensive retraining.
• Leverage Chain-of-Thought (CoT) prompting for structured, step-by-step reasoning in complex tasks.
• Evaluate model performance using BLEU, ROUGE, and other relevant metrics; identify opportunities for improvement.
• Deploy trained and fine-tuned models into production environments, integrating with real-time systems and pipelines.
• Identify, monitor, and mitigate issues related to bias, hallucinations, and knowledge cutoffs in LLMs.
• Work closely with cross-functional teams (data scientists, engineers, product managers) to design scalable and efficient NLP-driven Skills :
• 7+ years of overall experience in software / AI development with at least 2+ years in transformer-based NLP models.
• 4+ years of hands-on expertise with transformer architectures (GPT, BERT, T5, RoBERTa, etc.
• Strong understanding of attention mechanisms, self-attention layers, tokenization, embeddings, and context windows.
• Proven experience in fine-tuning pre-trained models for NLP tasks (summarization, classification, text generation, translation, Q&A).
• Expertise in prompt engineering, including zero-shot, few-shot, many-shot learning, and prompt template creation.
• Experience with instruction-based prompting and Chain-of-Thought prompting for reasoning tasks.
• Proficiency in Python and NLP libraries / frameworks such as Hugging Face Transformers, SpaCy, NLTK, PyTorch, TensorFlow.
• Strong knowledge of model evaluation metrics (BLEU, ROUGE, perplexity, etc.
• Experience in deploying models into production environments.
• Awareness of bias, hallucinations, and limitations in LLM to Have :
• Experience with LLM observability tools and monitoring pipelines.
• Exposure to cloud platforms (AWS, GCP, Azure) for scalable model deployment.
• Knowledge of MLOps practices for model lifecycle Key Skills :

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 : IT :

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

(ref : hirist.tech)