Senior AI Engineer

Location: Bnei Brak, Tel Aviv District, Israel; hybrid work environment

Company

hirify.global is a global video technology company providing live, on-demand, and real-time video products used by more than 1,000 organizations.

What you will do

• Build the shared platform layer for agentic AI, including orchestration, skills registry, evaluation, guardrails, memory, integrations, retrieval, and tracing.
• Develop shared infrastructure consumed by real-time conversational and offline video generation runtimes.
• Design systems for planning, sub-agents, parallel execution, tool calling, context management, and multi-agent coordination under latency and deadline constraints.
• Build registries, gateways, evaluation harnesses, tracing systems, and memory services for internal teams and external customers.
• Integrate open-source tooling into production systems and make build-versus-adopt decisions.
• Own platform components through production deployment, including integration with real-time pipelines and adoption by FDE teams.

Requirements

• 4+ years of experience building production backend or platform systems, including distributed services, APIs, asynchronous processing, and systems serving multiple consumers.
• Primary proficiency in Python and experience with high-throughput, low-latency services.
• Deep hands-on production experience with LLMs, including orchestration, tool calling, retrieval pipelines, context management, prompt chaining, and multi-agent coordination.
• Proficiency with LangChain, LangGraph, or equivalent orchestration frameworks.
• Experience building platform primitives such as registries, gateways, evaluation frameworks, tracing systems, or similar shared infrastructure.
• Understanding of contracts, versioning, and the distinction between shipping a platform and shipping a feature.
• Experience integrating open-source tooling into production systems and building proprietary layers where needed.
• Deep experience with RAG systems, including indexing strategies, retrieval evaluation, chunking, re-ranking, hybrid search, and retrieval failure modes.
• Familiarity with vector databases such as Pinecone, Weaviate, Qdrant, or similar, and with embedding models.
• Familiarity with real-time system constraints, including latency budgets, deadlines, and streaming architecture.
• Strong systems design skills for registries, gateways, memory services, and evaluation harnesses serving internal teams, external customers, real-time paths, and offline paths.

Nice to have

• Experience evaluating LLM systems, designing metrics, building test harnesses, measuring behavioral consistency, and detecting regressions; familiarity with DeepEval, Ragas, or similar.
• Experience with multi-tenant platforms, tenant isolation, scoped configuration, and preventing cross-customer data or behavior leakage.
• Background in speech or multimodal AI pipelines, including ASR, TTS, avatar rendering, or video generation.
• Experience with platform-level observability and tracing; familiarity with Langfuse, Opik, OpenTelemetry, or similar.
• Familiarity with CrewAI, AutoGen, Semantic Kernel, MCP, and failure modes in multi-step AI systems.
• Experience with AI guardrails and safety, including input filtering, output validation, grounding checks, and real-time streaming latency trade-offs.

Culture & Benefits

• Hybrid and flexible work environment.
• Extended private health insurance, including mental health coverage.
• Personal and professional development programs.
• Occasional cross-company long weekends.
• Diverse and collaborative environment with opportunities for growth and initiative.