דרושים AI Developer בתל אביב

We’re seeking an AI Developer to architect and deliver the intelligence behind a no-code app and agent platform. In this role, you’ll take full ownership of AI capabilities—from model selection and orchestration to inference, evaluation, and production-grade reliability. You’ll collaborate closely with Product and Design to transform complex user needs into elegant, scalable solutions, while setting a high standard for AI quality, safety, and performance across the company.

Key Responsibilities

• Lead the design and development of AI-powered features for our app and agent builder, covering everything from architectural design and prototyping to production deployment and monitoring.
• Build and maintain robust agent orchestration (tool/function calling, memory, workflows), retrieval pipelines (RAG), and low-latency inference services.
• Evaluate, integrate, and optimize LLMs and embeddings (OpenAI, Anthropic, open-source), including prompt engineering, guardrails/safety, and fine-tuning when needed.
• Develop secure and reliable integrations and SDKs to connect agents with external systems and data sources (REST/GraphQL APIs, webhooks, OAuth).
• Implement rigorous offline and online evaluation frameworks, experimentation processes, and observability tooling to ensure quality, correctness, and cost-efficiency at scale.
• Work cross-functionally to translate user challenges into intuitive solutions; mentor engineers and contribute to engineering best practices.
• Drive operational excellence across testing, CI/CD, performance optimization, reliability, security, and cost management.

Requirements

Required Qualifications & Skills

• 2+ years of professional software engineering experience, including at least 1-2 years building production-grade ML/AI or LLM-based systems.
• Strong Python skills and proficiency in TypeScript/Node.js (or similar), with a proven record of shipping production services.
• Hands-on experience with LLMs: prompt design, tool/function calling, retrieval-augmented generation (RAG), and agent frameworks (LangChain, LlamaIndex, Semantic Kernel) or custom orchestration.
• Solid data and infrastructure knowledge: vector databases (pgvector, Pinecone, Weaviate), search engines (Elasticsearch/OpenSearch), SQL databases (Postgres), and caching systems (Redis).
• Experience with cloud environments (AWS/GCP/Azure), containers (Docker), orchestration/serverless platforms (Kubernetes/Lambda), CI/CD, and observability tools.
• Strong understanding of API and distributed systems design, with an emphasis on reliability, performance, security, and cost-efficiency.
• A product-oriented mindset and excellent communication skills; comfortable owning solutions end to end in a fast-moving environment.
• Bachelor’s degree in Computer Science, Engineering, or equivalent practical experience.

Preferred Qualifications

• Experience building no-code/low-code platforms, visual builders, or workflow engines.
• Background in model customization (fine-tuning/LoRA, distillation, embeddings) and GPU inference optimization (vLLM, TensorRT/Triton).
• Familiarity with LLM evaluation and observability tools (Langfuse, Weights & Biases), A/B testing, and prompt/version management.

Open-source contributions, publications, or a strong portfolio of AI or agentic systems deployed to production.