Senior Generative AI Engineer

Position:

Experience:

Location:

Job Type :: Contract 2 Hire

Senior LLM Engineer

Key Responsibilities

• Design, develop, and optimize

  LLM-powered applications

  for text generation, summarization, question answering, classification, and translation.
• Fine-tune and adapt

  pre-trained transformer models

  (GPT, BERT, T5, RoBERTa, etc.) to

  domain-specific datasets

  .
• Implement

  prompt engineering techniques

  including zero-shot, few-shot, and many-shot learning to maximize model accuracy.
• Create reusable

  prompt templates

  for diverse use cases and ensure adaptability across contexts.
• Apply

  chain-of-thought (CoT) prompting

  for complex reasoning and problem-solving tasks.
• Continuously

  evaluate, test, and refine prompts

  to ensure output consistency and reliability.
• Mitigate issues related to

  biases, hallucinations, and knowledge cutoffs

  in model outputs.
• Collaborate with cross-functional teams to design and deploy

  scalable NLP/LLM solutions

  into production.
• Ensure high-quality deliverables using standard

  NLP evaluation metrics

  (BLEU, ROUGE, etc.).

Must-Have Skills

• 7+ years of overall experience, with at least 2+ years in

  transformer-based LLMs & NLP tasks

  .
• Deep expertise in

  transformer architectures, attention mechanisms, tokenization, embedding layers, and context windows

  .
• Proficiency in

  Python

  and strong hands-on experience with

  NLP libraries/frameworks

  (Hugging Face, SpaCy, NLTK).
• Strong understanding of

  instruction-based prompting, zero/few/many-shot learning techniques

  .
• Proven track record in

  training, fine-tuning, and deploying LLMs

  for production use cases.
• Experience with

  text evaluation metrics

  (BLEU, ROUGE, etc.).