Lead AI Engineer - Enterprise AI & RAG Architect

Granite Telecommunications; Quincy (MA); On-site; USD 180,000 - 280,000; Full time

Job summary

Granite Telecommunications seeks a Lead AI Engineer to design, build, and deploy enterprise AI/ML systems. You will lead the development of agentic AI to automate operations, and build RAG/ColBERTv2 pipelines for enterprise documents.

You will leverage LLMs and function calling to automate workflows and apply reinforcement learning for optimization. The role requires deep expertise in Python, PyTorch/TensorFlow, Hugging Face, LangChain, and RAG pipelines, with a focus on scalable, secure

Qualifications

• 5+ years of proven experience deploying production‑grade AI/ML systems.
• Strong programming skills in Python with PyTorch, TensorFlow, Hugging Face, and LangChain.
• Demonstrated expertise with LLM fine‑tuning (LoRA/PEFT), distillation, and optimization.
• Experience implementing RAG pipelines with embedding tech and vector stores (FAISS, Pinecone).
• Proven track record building agentic AI systems interfacing with multiple enterprise apps.

Responsibilities

• Develop and implement AI solutions using fine‑tuned LLMs (OpenAI, LLaMA, Mistral).
• Design and optimize RAG pipelines with advanced vector databases.
• Build and enhance agentic AI systems with LangChain, AutoGPT, or similar.
• Deploy ColBERTv2 architectures for semantic retrieval and classification.
• Ensure robust preprocessing/postprocessing to boost model performance and explainability.
• Collaborate with product, data science, and software teams.
• Implement best practices in model distillation, quantization, and deployment.
• Ensure compliance with security, privacy, and data governance.

Skills

Python

PyTorch

TensorFlow

Hugging Face

LangChain

LoRA/PEFT

RAG pipelines

vector stores (FAISS/Pinecone/Milvus)

reinforcement learning

LLM fine-tuning

Education

Bachelor’s degree in CS, Data Science, ML, AI

Master’s or PhD in CS/ML/AI

Tools

FAISS

Pinecone

Milvus

LangChain

AutoGPT

Docker

Kubernetes

Triton Inference Server

TensorRT

Job description

Granite Telecommunications seeks a Lead AI Engineer to design, build, and deploy enterprise AI/ML systems. You will lead the development of agentic AI to automate operations, and build RAG/ColBERTv2 pipelines for enterprise documents.

You will leverage LLMs and function calling to automate workflows and apply reinforcement learning for optimization. The role requires deep expertise in Python, PyTorch/TensorFlow, Hugging Face, LangChain, and RAG pipelines, with a focus on scalable, secure