LLM Engineer (AI)

A highly unique, profitable biotechnology startup that develops advanced computational biology platforms designed to model human physiology for clinical drug discovery.

Based on a decade of deep academic research conducted in collaboration with the Technion and Stanford University under the leadership of a world-renowned AI professor, the company builds high-fidelity computational models that predict drug interactions, isolate protein-molecule targets, and evaluate therapeutic efficacy across diverse populations.

By significantly reducing the industry’s reliance on animal testing and accelerating clinical pipeline design, the platform has secured multi-year partnerships with global pharmaceutical giants such as Pfizer, Roche, Sanofi, and Ferring.

The company is located in Tel Aviv (train-accessible) and operates on a hybrid model of two days of remote work.

Key Responsibilities

• Designing and implementing deterministic, multi-agent orchestration frameworks and cognitive automation pipelines utilizing Python.
• Building and optimizing advanced Retrieval-Augmented Generation (RAG) structures and Model Context Protocols (MCP) tailored for complex scientific documentation.
• Structuring rigorous validation frameworks, continuous profiling benchmarks, and analytical metrics to evaluate Large Language Model (LLM) performance and accuracy tradeoffs.
• Scaling distributed production backend services capable of handling highly complex, non-deterministic execution paths in real time.
• Participating in code design reviews and system architecture scaling sessions to maintain clean, modular, and maintainable platform repositories.
• Tech Stack & Core Domains- Python, Agentic AI, Multi-Agent Systems, LLMs (OpenAI, Anthropic), LangChain, RAG, MCP, LLM Evaluation, Production AI Infrastructure, Computational Biology, and Scientific Workflows.

Requirements-

• 5+ years of professional software engineering experience deeply focused on applied AI, ML systems, or complex data-heavy architectures (Mandatory).
• Proven track record of owning, scaling, and deploying production-grade software systems from inception to release (Mandatory).
• Strong, production-grade programming and architecture proficiency utilizing Python alongside solid software engineering fundamentals (Mandatory).
• Hands-on engineering experience with benchmarking, evaluation, and validation of LLM/agent-based systems, including defining success metrics, running experiments, and analyzing performance tradeoffs (Mandatory).
• Direct, practical experience constructing intelligent applications utilizing LLMs and agentic frameworks (e.g., LangChain, OpenAI APIs, Anthropic SDKs, or similar orchestration tools) (Mandatory).
• Demonstrated experience building internal developer tools, enterprise analytics products, or high-scale customer-facing software components.
• Exceptional analytical and problem-solving skills, with a proven ability to independently drive execution inside ambiguous, fast-moving research-driven environments.