Back to jobs

Senior Generative AI Engineer (Python, LLM, RAG)

Mamsys World
Mississauga, Ontario, Canada
Full-time
AI tools:
OpenAI
Gemini
Claude
LangChain
LlamaIndex
Pinecone
Applications go directly to the hiring team

Full Description

Senior Generative AI Engineer (Python, LLM, RAG)

Location: Mississauga, Canada (Hybrid)

Full-Time

Role Overview:

We are hiring experienced Generative AI Engineers to design and build enterprise-grade AI solutions within the banking domain. This role focuses on developing scalable LLM-powered applications, implementing advanced RAG pipelines, and deploying production-ready AI systems.

The ideal candidate will have strong Python expertise, hands-on experience with LLMs and GenAI frameworks, and a deep understanding of end-to-end AI/ML lifecycle and MLOps practices.

Key Responsibilities:

* Design and develop Generative AI applications using Large Language Models (LLMs)

* Build and optimize Retrieval-Augmented Generation (RAG) pipelines with advanced techniques

* Develop scalable APIs and microservices using Python (FastAPI, Flask, etc.)

* Implement prompt engineering strategies, prompt tuning, and reusable templates

* Integrate LLM solutions with enterprise systems via APIs, knowledge graphs, and orchestration frameworks

* Work with vector databases (Pinecone, PGVector, Mongo Atlas, Neo4j) for semantic search and retrieval

* Handle and process large-scale unstructured datasets

* Deploy AI/ML models into production with strong MLOps practices

* Build and maintain CI/CD pipelines for AI solutions

* Ensure model performance, reliability, and safety using guardrails and evaluation frameworks

* Collaborate with cross-functional teams to deliver high-impact AI solutions

Required Skills & Qualifications:

Experience:

* 6–10 years in application development, AI/ML, or systems engineering

Core AI/ML Expertise:

* Strong foundation in:

* Machine Learning & Data Science

* Natural Language Processing (NLP)

* Neural Networks & LLMs

* Statistics

Generative AI & LLMs:

* Hands-on experience with:

* OpenAI, Google Gemini, Anthropic Claude, Mistral, LLaMA

* Strong experience with:

* RAG pipelines (must-have)

* Prompt engineering & tuning

* Agentic frameworks (LangChain, LlamaIndex, etc.)

* Guardrails & GenAI evaluation techniques

Programming & Tools:

* Strong proficiency in Python

* Experience with:

* Pandas, NumPy, scikit-learn

* PyTorch / TensorFlow

* Transformers, Hugging Face

* FastAPI

* LangChain, LlamaIndex

Data & Infrastructure:

* Experience with:

* Vector databases: Pinecone, PGVector, MongoDB Atlas, Neo4j

* Handling large-scale unstructured data

Deployment & MLOps:

* Experience deploying AI models to production

* Strong understanding of:

* MLOps, model evaluation

* CI/CD tools: Jenkins, GitLab CI, Azure DevOps, ArgoCD

Cloud & Containerization:

* Hands-on experience with:

* Kubernetes / OpenShift

* Cloud platforms (GCP, Azure, AWS preferred)

Soft Skills:

* Strong analytical and problem-solving skills

* Ability to work independently in complex environments

* Excellent communication and collaboration skills

Applications go to the hiring team directly