SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Immunai is an AI-driven platform company focused on improving drug discovery and development by decoding the human immune system. The company combines large-scale single-cell immune data, advanced machine learning, and strong engineering to help pharmaceutical and research partners make better decisions throughout the drug development process.
You will join as an AI Infrastructure Engineer to build the foundation enabling AI agents to reliably access and operate Immunai's internal systems, including code repositories, pipelines, datasets, and compute infrastructure. This is a software infrastructure role focused on building systems that enable AI agents to operate effectively and safely—not a scientific modeling position.
Key responsibilities:
- Design and maintain infrastructure enabling AI agents to interact with internal systems, data, and compute resources
- Establish testing, CI/CD, and evaluation standards for agentic workflows to ensure quality and reliability
- Build permissions, approvals, and audit mechanisms for autonomous agents to implement safety controls
- Monitor agent behavior and usage patterns to drive continuous improvement in reliability and performance
- Support reliable autonomous and multi-agent operations across teams and users at scale
- Manage performance, infrastructure costs, and compute utilization for efficiency
- Partner with research and engineering teams to enable AI-driven workflows and remove blockers
The role is hybrid, based in Ramat Gan, Israel.
REQUIREMENTS:
Required:
- BSc or MSc in Computer Science, Software Engineering, or related field (mandatory)
- Hands-on production experience with LLMs and agentic systems (agent frameworks, tool use, MCP, etc.) with proven reliability track record (mandatory)
- 5+ years of hands-on software engineering experience designing modular, maintainable systems
- Proficiency in Python and cloud environments (GCP or AWS)
- Experience with LLM/agent evaluation frameworks
- Experience with CI/CD, testing, and observability
Preferred:
- Experience with ML pipelines, experiment tracking, or MLOps tools (e.g., ClearML)
- Background in biomedical or other data-intensive environments
- Personal traits: impact-driven, collaborative, execution-focused, striving for excellence, effective cross-cultural collaboration, growth mindset, candid and authentic communication
