Senior AI Compiler Front-End Engineer

Описание вакансии

#vacancy #hot #English #AI #LLM #ML #remote #Python

Senior AI Compiler Front-End Engineer

Elinext is an international IT company specializing in software development and integration for customers worldwide. We help businesses build reliable, scalable, and modern digital solutions across a wide range of industries.

We are looking for a Senior AI Compiler Front-End Engineer to join a team working on the development of an AI/ML compiler front-end.

In this role, you will be responsible for building and improving model conversion pipelines that translate models from frameworks such as ONNX, TensorFlow, and PyTorch into an internal Intermediate Representation (IR). You will work at the intersection of compiler engineering, machine learning systems, and modern AI architectures, helping to deliver a scalable and production-ready AI compiler stack.

This is a strong senior-level role for an engineer who combines hands-on technical depth with the ability to work across teams and contribute to architecture and technical direction.

Responsibilities

• Design and develop the front-end layer of an AI/ML compiler
• Build and improve model conversion pipelines from ONNX, TensorFlow, and PyTorch into an internal IR
• Work on graph parsing, graph transformations, and model optimization
• Implement and improve compiler transformations, pattern matching, and graph rewriting
• Contribute to support for modern AI model architectures, including CNNs, Transformers, and LLMs
• Collaborate closely with compiler backend, runtime, performance, and hardware teams
• Help ensure the compiler stack is scalable, efficient, and production-ready
• Participate in technical discussions, architecture decisions, debugging, and performance improvement

Requirements

• Strong commercial experience in compiler development, ML systems, or AI infrastructure
• Strong Python programming skills
• Good understanding of software architecture and maintainable system design
• Solid understanding of Intermediate Representations (IRs)
• Solid understanding of graph-based computation models
• Solid understanding of compiler transformations and optimizations
• Solid understanding of pattern matching and graph rewriting
• Hands-on experience with ONNX, TensorFlow, and PyTorch
• Experience with graph parsing, graph transformations, and ML model optimization
• Good understanding of modern AI architectures such as CNNs, Transformers, and LLMs
• Strong debugging and problem-solving skills
• Ability to work independently and collaborate effectively with cross-functional engineering teams

Nice to Have

• Experience working on production-grade AI compiler stacks
• Experience optimizing models for performance and hardware efficiency
• Familiarity with runtime systems, low-level performance optimization, or hardware-aware compilation
• Previous experience in technically complex AI infrastructure projects

💼 What We Offer

• Small-company feel within a fast-growing international environment
• Friendly, collaborative, and mission-driven team
• Health & retirement benefits
• Vacation plus 5 additional paid sick days
• Medical insurance
• Discounts in various establishments depending on the country
• Monetary bonuses for important life events
• Long-service benefits, including additional vacation days and other perks
• Corporate events and team-building activities
• Corporate English courses
• Support with professional certifications and reimbursement for professional courses and training