Senior AI Engineer

Company Overview:

Position Overview:

Join Cellebrite’s Forensic Research Group and take part in uncovering hidden data across mobile applications and cloud ecosystems. The team identifies, analyzes, and extracts forensic artifacts from mobile apps, APIs, cloud services, and raw binary data.

The team specializes in black-box reverse engineering and advanced mobile analysis across Android and iOS.

As an AI Engineer, you'll work hands-on with leading LLMs and the broader agentic ecosystem, applying cutting-edge frameworks and techniques to build, evaluate, and iterate on solutions. Your work will span the entire software lifecycle — from rapid prototypes and POCs to production-grade systems. Implement solid design, flexible implementation, strong telemetry, and production feedback loops.

Your responsibilities will be:

• Design and maintain a LangGraph-based Agent Harness optimized for online and offline/on-premise deployment, using hybrid LLM and deterministic layers to balance speed, memory, and costs.
• ​Own the complete evaluation lifecycle, including datasets, benchmarking frameworks, and automated regression testing to ensure output accuracy.
• ​Standardize tool-calling interfaces for forensic engines and collaborate with researchers to operationalize AI models into Cellebrite’s products.

• Bachelor’s degree in computer science or an engineering-related field.
• 6+ years of experience in software development.
• Proven experience as a Python developer.
• Experience with Agent Orchestration Framework (like LangGraph)
• Experience with the Agentic AI architecture, MCP, and A2A.
• Solid understanding of RAG pipelines, vector databases, embeddings, and retrieval techniques (chunking, indexing, filtering, relevance tuning)
• Experience with AI evaluation frameworks, prompt testing, or offline/online quality measurement
• Attention to detail, ability to multitask, and strong interpersonal skills.

Preferred:

• Experience in enterprise-scale application development in a SaaS environment.
• Strong observability design across infrastructure and AI workloads (metrics, logging, tracing, AI quality signals)
• Experience with an OOP language

#LI-AS1