ML Benchmarking & Infrastructure Engineer

Immunai; United States; Hybrid; USD 88,000 - 122,000; Full time

Job summary

Immunai in Ramat Gan, Israel, is seeking an ML Infra Engineer to own benchmarking and evaluation of foundation models and multimodal systems. You will support model development, iteration, and validation, and build out the ML engineering infrastructure for evaluation and deployment.

This role sits at the intersection of software engineering and applied AI, shaping how models are built and compared across the organization, with a hybrid work model.

Qualifications

• Bachelor's/Master's/PhD in computer science or related field.
• Strong software engineering skills with modular systems.
• Hands-on experience with ML models and evaluation pipelines.
• Proficiency in Python and modern ML ecosystems.
• Ability to read, modify, and debug deep learning models.
• Experience with benchmarks, metrics, or evaluation frameworks (preferred).
• Familiarity with foundation models or multimodal learning (preferred).
• Comfort navigating complex datasets and doing targeted exploratory analysis.
• Experience in biomedical or data-intensive domains (a plus).

Responsibilities

• Own & evolve benchmarking for foundation models and multimodal AI systems.
• Define core abstractions for datasets, tasks, models, metrics, and evaluation workflows.
• Develop metrics capturing predictive performance, biological relevance, and multimodal alignment.
• Support model development by collaborating with AI scientists and data scientists.
• Bring in new models and baselines to benchmarks and ensure meaningful comparisons.
• Explore data and results to debug evaluations and understand model behavior.
• Ensure evaluations are versioned, consistent, and reproducible over time.

Skills

Python

ML evaluation

Software engineering

Data exploration

Education

BSc/MSc/PhD in CS or related

Job description

Immunai in Ramat Gan, Israel, is seeking an ML Infra Engineer to own benchmarking and evaluation of foundation models and multimodal systems. You will support model development, iteration, and validation, and build out the ML engineering infrastructure for evaluation and deployment.

This role sits at the intersection of software engineering and applied AI, shaping how models are built and compared across the organization, with a hybrid work model.