Professional, Engineering

Bombardier Transportation GmbH; Dorval; On-site; CAD 80,000 - 110,000; Full time

Job summary

A leading aerospace company located in Dorval, Canada is seeking an experienced Software Engineer with a focus on AI and Machine Learning. Responsibilities include improving retrieval systems, modernizing front-end applications, and ensuring data security. The ideal candidate will have over 7 years of experience, strong skills in Python, and expertise with Azure services. This position offers a comprehensive benefits program and opportunities for growth.

Benefits

Comprehensive insurance plans

Retirement savings plan

Employee Assistance Program

Qualifications

• 7+ years in software engineering and 2+ years in GenAI for search/RAG.
• Hands-on experience with BGE or similar technologies.
• Comfortable with Azure and relevant access control integrations.

Responsibilities

• Lead improvements to retrieval quality.
• Redesign chunking and indexing for PDFs.
• Contribute to a modern frontend project.

Skills

Python

Information Retrieval Fundamentals

DevOps CI/CD

PaddleOCR

Azure

React/Next.js

Job description

Press Tab to Move to Skip to Content Link

Select how often (in days) to receive an alert:

When applicable, Bombardier promotes flexible and hybrid work policies.

At Bombardier, we design, build and maintain the world’s peak-performing aircraft for the world’s most discerning people and businesses, governments and militaries. We have been successful in setting the highest standards by putting our people at the heart of it all, and defining excellence, together.

Working at Bombardier means operating at the highest level. Every day, you are part of a team that delivers superior experiences and products, pushing the boundaries of what's possible in our industry and beyond. By prioritizing employee growth and development, we empower everyone to reach their full potential on their own terms, because the best work happens when you are free to be yourself and share your unique expertise.

With our employees’ well-being top of mind, we offer a comprehensive and competitive Benefits Program, which includes the following:

• Insurance plans (Dental, medical, life insurance, disability, and more)
• Retirement savings plan
• Employee Assistance Program

Process and Tools – Artificial Intelligence / Machine Learning

What are your contributions to the team?

• Lead improvements to retrieval quality: strengthen hybrid BM25 + dense retrieval, add robust metadata filtering, and implement/compare rerankers (cross-encoder or lightweight LLM-as-reranker) while iterating on existing BGE pipelines.
• Redesign chunking and indexing for PDFs (overlap/hierarchical, section-aware/semantic); build benchmarks to compare strategies; introduce dedup/versioning and maintain document lineage with structured citations.
• Expand evaluation beyond Recall@k (e.g., nDCG, MRR, Precision@k) and stand up a continuous evaluation pipeline with meaningful telemetry/logging (OpenTelemetry is a plus).
• Advance OCR & document understanding: use PaddleOCR for scanned PDFs; evaluate advanced LLM-based OCR approaches (local/on‑prem only); expand table/diagram extraction and prepare for multimodal retrieval.
• Contribute to a modern frontend: help migrate from Streamlit to React/Next.js + TypeScript (Node.js) with secure sign-in and PDF snippet highlighting.
• Strengthen security & platform foundations: implement access control with Azure AD (Entra ID) or LDAP; work comfortably in Azure; uphold Canada-only data residency and no external calls in design and deployment.
• Elevate developer experience: drive reviews, testing, and CI/CD workflows with Git Actions.

How to thrive in this role?

• Experience: 7+ years software engineering and 2+ years applied GenAI for search/RAG; strong Python and IR fundamentals (BM25, ANN/vector search, hybrid/fusion, reranking).
• Embeddings & reranking: Hands‑on with BGE (or similar) and lightweight tuning for embedders/rerankers; ability to build evaluation harnesses (offline metrics, curated sets, continuous runs).
• Docs & OCR: Practical PDF parsing; PaddleOCR; exposure to table/diagram extraction.
• Cloud & access control: Comfortable in Azure; familiarity with Azure AD or LDAP integration.
• DevOps: Git power‑user with CI/CD using Azure Devops git Actions.
• Nice to have: React/Next.js + TypeScript (Node.js); OpenTelemetry; query rewriting and LoRA/contrastive tuning; exposure to vector stores such as Qdrant, Milvus, Weaviate, pgvector (ChromaDB or equivalent also useful).

Now that you can see yourself in this role, apply and join the Bombardier Team!

Bombardier is an equal opportunity employer and encourages persons of any race, religion, ethnicity, gender identity, sexual orientation, age, immigration status, disability or other applicable legally protected characteristics to apply.

Job Process and Tools - Artificial Intelligence / Machine Learning

Primary Location Administrative Centre (CA)

Organization Aerospace Canada

Shift Day job

Employee Status Regular