Senior Machine Learning Engineer to develop a POC for a LLM-powered internal chatbot for internal information using machine leaning packages for a healthca

Our valued healthcare client is seeking a Senior Machine Learning Engineer to develop a POC for a LLM-powered internal chatbot for internal information using machine leaning packages!

Initial 7-month contract (100% Remote), with possibility of extension. 7.25 hours per day, Monday to Friday. Candidates with the ability to work on-site in North York, ON or Ottawa, ON will be preferred.

As the successful candidate you will be leading the system design and implementation of ML solutions focused on RAG pipelines, LLMs, and production-grade infrastructure for NLP systems that combine structured and unstructured data from multiple sources.

Responsibilities:

• Build LLM-powered APIs and Chatbot Assistants using LangChain, LlamaIndex, or similar frameworks.
• Work with vector databases like pgvector, Weaviate, or Pinecone to store and retrieve document embeddings.
• Ingest and process data from sources like SharePoint, Documents, GitLab, Confluence, Databases, Wikis, and more.
• Design and integrate new use cases for the NLQ (Natural Language Querying) product by working with data pipelines and enhancing prompt engineering.
• Train or fine-tune lightweight models for intermediate NLP requirements.
• Develop and iterate on the existing ML pipeline, including containerized services deployed via Docker and Kubernetes.
• Enforce MLOps standards, and Integrate ML Product consumption through platforms such as MS Teams, Code Editors (VS Code, RStudio)

Required Skills:

• 2+ years of experience deploying and optimizing LLMs (large language models) in production environments, including model serving infrastructure, inference optimization (quantization, pruning, caching), performance monitoring, and bias mitigation
• 3+ years of experience building and deploying Machine Learning and Deep Learning models, including classical ML algorithms, RNNs, LSTMs, Transformers, GANs, and Graph Neural Networks
• 3+ years of hands-on experience with NLP (Natural Language Processing) tasks such as Neural Machine Translation, Text Generation, Summarization, Sentiment Analysis, and Question Answering
• 3+ years of experience implementing Retrieval-Augmented Generation (RAG) pipelines including text preprocessing (chunking, embedding), optimizing retrieval, and integrating vector databases for similarity search
• 3+ years of experience with Python and SQL, and strong proficiency in ML/LLM frameworks such as PyTorch, TensorFlow, LangChain, LlamaIndex, FAISS, Haystack, and Sentence Transformers
• 3+ years of experience developing and deploying REST APIs and containerized services using Docker, AWS ECS, and AWS ECR