C
AI Engineer - Agentic AI Platform Infrastructure
·Israel
Not specifiedFull-timeAI Engineering
Hands-on AI Engineer role focused on building the core infrastructure behind an agentic AI platform. You will design and develop shared platform components, LLM infrastructure, and multi-agent systems to enable scalable enterprise deployments.
Responsibilities
- Build and scale core backend infrastructure for an agentic AI platform.
- Design and develop shared platform components: orchestration services, registries, gateways, evaluation systems, tracing, memory, and retrieval infrastructure.
- Work on LLM infrastructure including tool calling, context management, RAG pipelines, prompt chaining, and multi-agent coordination.
- Create reliable platform services supporting multiple internal teams and enterprise customers.
- Evaluate and integrate open-source AI tooling where appropriate.
- Design systems with versioning, tenant isolation, scoped configuration, observability, and platform-grade reliability.
- Partner with product, engineering, and customer-facing teams to turn recurring needs into reusable platform capabilities.
- Ensure performance, latency, reliability, and safety in all systems.
Requirements
- 4+ years of experience building production backend or platform systems, including distributed services, APIs, async processing, and multi-consumer infrastructure.
- Strong Python experience, with exposure to high-throughput or low-latency backend environments.
- Hands-on production experience with LLM systems, including orchestration, tool/function calling, retrieval pipelines, context management, and multi-agent workflows.
- Experience with agent frameworks such as LangChain, LangGraph, Semantic Kernel, CrewAI, AutoGen, or similar.
- Experience building platform primitives such as registries, gateways, evaluation tools, tracing systems, memory services, or shared infrastructure.
- Strong understanding of RAG systems, including indexing, retrieval evaluation, chunking, re-ranking, hybrid search, and common failure modes.
- Familiarity with vector databases such as Pinecone, Weaviate, Qdrant, or similar.
- Strong systems design skills and ability to build scalable, reusable infrastructure.
- Ability to make practical build-versus-adopt decisions with open-source and commercial AI tooling.
Nice to have
- Experience building evaluation frameworks for LLM or agentic systems, including metrics, test harnesses, regression detection, and quality measurement.
- Familiarity with tools such as DeepEval, Ragas, Langfuse, Opik, OpenTelemetry, or similar.
- Experience with multi-tenant SaaS platforms, including tenant isolation, scoped configuration, and data separation.
- Background in conversational AI, speech, multimodal AI, or real-time AI systems.
- Experience with guardrails, safety mechanisms, input filtering, output validation, and grounding checks.
- Understanding of latency-sensitive architectures, especially in real-time or streaming environments.
- Experience creating infrastructure that enables multiple teams or customers to build on a shared platform.