AI Engineer (Agentic AI)

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 across real-time conversational and offline video generation runtimes.
• Develop orchestration capabilities including planning, sub-agents, tool calling, parallel execution, and deadline-aware processing.
• Build platform primitives such as skills registries, evaluation harnesses, guardrails, integration gateways, memory services, and tracing infrastructure.
• Develop retrieval infrastructure and RAG capabilities, including indexing, retrieval evaluation, chunking, re-ranking, hybrid search, vector databases, and embeddings.
• Design high-throughput, low-latency distributed services and APIs for multiple internal teams and external customers.
• Make build-versus-adopt decisions and integrate open-source AI and platform tooling into production systems.

Requirements

• 4+ years of experience building production backend or platform systems with distributed services, APIs, asynchronous processing, and multiple consumers.
• Strong Python experience and hands-on production experience with LLM infrastructure, orchestration, tool calling, retrieval pipelines, context management, prompt chaining, and multi-agent coordination.
• Experience with LangChain, LangGraph, or equivalent orchestration frameworks.
• Deep experience with RAG systems, vector databases such as Pinecone, Weaviate, or Qdrant, and embedding models.
• Strong systems design skills, including registries, gateways, memory services, evaluation harnesses, contracts, and versioning.
• Understanding of real-time latency constraints, streaming architecture, observability, tenant isolation, and production reliability.

Nice to have

• Experience evaluating LLM systems with metrics, test harnesses, regression detection, DeepEval, Ragas, or similar tools.
• Experience with multi-tenant platforms, speech or multimodal AI pipelines, observability, and platform-level tracing.
• Familiarity with Langfuse, Opik, OpenTelemetry, CrewAI, AutoGen, Semantic Kernel, or MCP.
• Experience implementing AI guardrails, safety controls, grounding checks, and output validation.

Culture & Benefits

• Hybrid work model with a flexible working environment.
• Collaborative culture where initiative and participation are encouraged.
• Opportunities to work on enterprise-grade AI infrastructure consumed by multiple teams and customers.
• Global organization with offices in New York, London, Singapore, and Tel Aviv.