Software Engineer

General Summary of Position:

Granite seeking a talented and motivated Software Engineer to join our team. The Software Engineer will be responsible for designing, developing, and implementing cutting-edge AI and machine learning solutions that solve complex business problems and improve our products or services. The ideal candidate should have a strong background in machine learning, deep learning, and data analysis, as well as a passion for staying updated on the latest developments in the field

 

The right candidate will be a self-starter, able to work independently or as a team member.  Must be able to thrive in a fast-paced environment and learn new technologies quickly.  This is a growing company where you will be able to have a significant impact on our internal processes and get a chance to add directly to the goals of the organization.

 

Duties and Responsibilities: 

  Data Collection & Preparation 

• Gather and preprocess multimodal data for AI/ML models, including cleaning, augmentation (e.g., RAG for text enrichment), and synthetic data generation. 
• Implement embedding techniques (e.g., BERT, sentence-transformers) for semantic feature extraction. 

  Model Development 

• Design and deploy AI/ML models, including neural networks (transformers, LLMs), decision trees, and ensemble methods. 
• Specialize in prompt engineering, Model Context Protocol design, and function calling integrations for LLM-based applications. 
• Apply supervised fine-tuning (SFT) for domain-specific adaptation of pre-trained models. 

  Training & Evaluation 

• Optimize models using frameworks like LangChain for context-aware workflows. 
• Evaluate performance with metrics tailored to generative AI (e.g., coherence, retrieval accuracy). 

  Feature Engineering 

• Leverage embeddings and attention mechanisms to enhance model interpretability and efficiency. 

  Model Deployment 

• Deploy scalable, servable AI applications on GCP using Vertex AI, Cloud Run, or Kubernetes. 
• Implement Model Guard frameworks for output validation, bias mitigation, and ethical compliance. 

  Continuous Learning 

• Stay updated on advancements in LLMs, RAG architectures, and emerging tools (e.g., LangChain, LlamaIndex). 

  Collaboration 

• Partner with cross-functional teams to align AI solutions (e.g., function calling, Model Context Protocol) with business use cases. 

  Documentation 

• Detail prompt templates, RAG pipelines, and fine-tuning procedures for reproducibility. 

  Security & Privacy 

• Ensure compliance with data governance standards in AI workflows (e.g., anonymization in embeddings, Model Guard audits).

Required Qualifications:

 

  Education 

• Master’s or Bachelor’s degree (or higher) in computer science, data science, artificial intelligence, machine learning, or a closely related field. 

  Deep Learning Expertise 

• Proficiency in deep learning frameworks such as TensorFlow and PyTorch, with hands-on experience in neural network architectures including CNNs, RNNs, and advanced transformer models (e.g., BERT, GPT). 
• Experience with retrieval-augmented generation (RAG) systems and prompt engineering for LLMs. 

  M