AI Engineer - Automotive
Hybrid Cluj Full-time Mid-level AI Engineering
At a glance
Mid-level AI Engineering role at Qualysoft. Cluj · full-time.
Pay not stated AI Engineer salary
RoleAI Engineering
SeniorityMid-level
LocationCluj
WorkplaceHybrid
EmploymentFull-time
PostedJul 13, 2026 · 3mo ago
Role brief
aimlroles summary, based on the employer's posting.
What you'll do
- Build and tune generative AI applications, focusing on model evaluation, retrieval-augmented generation and prompt design
- Create RAG workflows from document intake through retrieval and re-ranking, connecting them to internal data
- Set up AI data storage with Snowflake vector search and relational databases such as PostgreSQL
- Improve source data quality and test LLM options for reliable performance across business use cases
- Add testing, monitoring, security and performance practices, while working with platform and business teams
What you bring
- A university qualification in computer science, engineering or a related discipline
- At least seven years building software, especially backend or data-heavy systems
- Strong Python skills and a track record of delivering production systems
- Practical LLM API, orchestration and RAG experience, including vector databases or embeddings
- Experience with LLM data preparation, safety checks and evaluation, plus strong written and spoken English
Who this fits
This mid-level role is based in Cluj, Romania, with a hybrid arrangement and openness to remote work. You’ll suit work that combines hands-on backend engineering with collaboration across AI platform and business teams.
From the employer
About Qualysoft
· 25 years of experience in software engineering, established in Vienna, Austria
· Active in Romania since 2007, with office in central Bucharest (Bd. Iancu de Hunedoara 54B)
· Delivering End to End IT Consulting Services - From Team Augmentation and Dedicated Teams to Custom Software Development
· We deliver scalable enterprise systems, intelligent automation frameworks, and digital transformation platforms
· Cross-industry experience by sustaining global players in BSFI (Banking, financial services and insurance), Telecom,Retail & E-commerce, Energy and Utilities, Automotive, Manufacturing, Logitics, High Tech
· Global Presence: Switzerland, Germany, Austria, Sweden, Hungary, Slovakia, Serbia, Romania, and Indonesia
· International team of 500+ software engineers
· Strategic partnerships: Microsoft Cloud Certified Partner, Tricentis Solutions Partner in Test Automation and Test Management, Creatio Exclusive Partner, Doxee Implementation Partner
· Powered by cutting-edge technologies: AI, Data & Analytics, Cloud, DevOps, IoT, and Test Automation.
· Project beneficiaries ranging from large-scale enterprises to startups
· Stable growth and revenue increase year over year, a resilient organisation in volatile IT market conditions
· Quality-first mindset, culture of innovation, and long-term client partnerships
· Global and local reach – trusted by key industry players in Europe and the US
Responsibilities:
- • Drive the architecture, development and optimization of (generative) AI applications with a strong focus on
model evaluation, retrieval-augmented generation (RAG), and prompt engineering.
• Implement end-to-end RAG pipelines (ingestion, chunking, embeddings, retrieval, re-ranking) and integrate them
with internal data sources.
• Design and integrate data storage for AI applications using vector search in Snowflake and relational databases
such as PostgreSQL.
• Analyze and integrate data from various sources, ensuring high data quality and preparing it for effective AIdriven solutions.
• Experiment with LLM models (e.g. OpenAI, Anthropic, Azure OpenAI) to improve performance, reliability and
applicability across business use cases.
• Establish and maintain robust engineering practices for GenAI applications (testing, observability, security,
performance optimization).
• Collaborate closely with our AI platform team to enhance, standardize and scale AI-driven capabilities across the
BMW Group.
• Work closely with different business units, helping them leverage AI models for real-world applications and
continuous improvements.
• Share your expertise in Generative AI, LLM orchestration, and software engineering with other teams,
contributing to knowledge-sharing and innovation within the organization.
Qualifications:
- • University degree in Computer Science, Engineering, or a related field.
• At least 7 years of professional software engineering experience, with a strong focus on backend or dataintensive applications.
• Strong proficiency in Python and experience building production systems.
• Strong understanding of software development best practices (clean code, unit/integration testing, code
reviews, CI/CD).
• Hands-on experience with LLM APIs (e.g. OpenAI, Anthropic, Azure OpenAI) and LLM orchestration frameworks
such as LangGraph.
• Proven experience with RAG architectures and vector databases / embeddings.
• Experience with data ingestion and preprocessing for LLM applications (ETL, data pipelines, document
processing).
• Experience implementing guardrails, safety checks and evaluation frameworks for LLM applications.
• Familiarity with MLOps or LLMOps concepts and best practices for deploying, monitoring and maintaining AI
models and AI-enabled services in production.
• Strong problem-solving skills and the ability to work in a collaborative, agile environment.
• Excellent English communication skills, both written and spoken.
*We are an equal opportunity employer and value diversity. All employment decisions are made without regard to age, gender, disability, race, ethnicity, religion, sexual orientation, or any other protected characteristic. We encourage applicants from all backgrounds to apply.*