NLP/LLM Specialist

Stantec; Old Toronto; Hybrid; CAD 80,000 - 110,000; Full time

Job summary

An innovative firm is seeking a talented NLP/LLM Specialist to join their dynamic ML team. In this pivotal role, you will design, develop, and optimize NLP chatbots and agents on a cutting-edge digital platform. Your expertise in retrieval augmented generation and LLM foundation models will be essential in driving initiatives forward. With a flexible hybrid work schedule, this position offers the chance to collaborate with cross-functional teams and stay at the forefront of AI advancements. If you're passionate about making an impact in the AI space, this opportunity is for you.

Qualifications

• 3-5 years experience in software engineering or AI roles.
• Strong proficiency in Python and SQL, with orchestration tools experience.

Responsibilities

• Design and implement LLM application architecture for data retrieval.
• Lead chatbot and agent deployment using Databricks and Azure.

Skills

Natural Language Processing

Large Language Models

Python

SQL

Cloud Platforms (Azure, AWS, GCP)

Machine Learning

Data Science

Education

Bachelor's degree in Computer Science

Master's degree in related field

Tools

Databricks

PyTorch

TensorFlow

Hugging Face Transformers

LangChain

LlamaIndex

Job description

Grow with the best. Join a smart, creative, and inspired team that accomplishes operational excellence. Bringing together individuals with diverse backgrounds, talents, and expertise, our 31,000 team members in over 450 locations worldwide are vital to making our Company stronger.

We are seeking a talented Natural Language Processing and Large Language Model (NLP/LLM) Specialist to join our dynamic enterprise ML team. As an NLP/LLM Specialist, you will play a crucial role in designing, developing, and optimizing NLP chatbots and agents within our digital platform based on Azure, utilizing Databricks and OpenAI services. Your expertise in retrieval augmented generation (RAG) chains and LLM foundation models will be instrumental in driving our initiatives forward. This position offers a flexible hybrid work schedule.

Your Key Responsibilities

1. Design LLM application architecture for retrieval over both structured and unstructured data, and implement smart agentic request routing for efficient token usage.
2. Lead the creation and deployment of chatbots and agents by leveraging Databricks, Azure vector stores, and serverless endpoint capabilities.
3. Contribute to the development of enterprise model governance, observability, and quality standards, leveraging tools like Databricks Unity Catalog.
4. Develop and align the product roadmap and vision with business goals.
5. Collaborate with cross-functional teams to understand data requirements and translate them into reliable, high-quality AI solutions.
6. Stay updated on the latest advancements in AI technologies.

Your Capabilities and Credentials

• Proven experience with Cloud Platforms such as Azure, AWS, or GCP.
• Strong proficiency in Python and SQL, with experience using orchestration tools like LangChain or LlamaIndex.
• Deep understanding of transformer-based models, including training processes and performance assessment of models like BERT.
• Proficiency with ML frameworks such as PyTorch, TensorFlow, and Hugging Face Transformers is preferred.

Education and Experience

• Bachelor’s degree in Computer Science, Engineering, or a related field; Master’s degree preferred.
• Minimum of 3-5 years of experience in software engineering, machine learning, data science, or AI roles.

This description is not exhaustive and responsibilities may evolve. Join us to build on your talents, do exciting work, and make an impact on the world around us.

Location: Toronto, Canada

Organization: BC-1299 Innovation-CA Digital COE

Employee Status: Regular

Job Level: Nonmanager

Travel: No

Schedule: Full-time

Job Posting Date: 27/01/2025

Req ID: REQ250000BO