Senior AI Engineer

Kaltura

. Build the shared platform layer that makes Kaltura's agentic AI extensible, measurable, and self-improving .

Posted 10/25/2026full-timeIsraelSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in building production backend/platform systems with a focus on high-throughput, low-latency services and orchestration frameworks. Proficient in Python and experienced with LLMs, RAG systems, and real-time system constraints.

Highest-signal resume keywords

Python ProgrammingLLM Production ExperienceOrchestration FrameworksHigh-Throughput ServicesSystems Design Skills

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Distributed ServicesAPIsAsync ProcessingPlatform PrimitivesRAG SystemsIndexing StrategiesRetrieval EvaluationChunkingRe-RankingHybrid Search

Soft Skills

Decision-MakingProblem-Solving

Tools & Technologies

LangChainLangGraphPineconeWeaviateQdrantDeepEvalRagasLangfuseOpikOpenTelemetry

Industry Keywords

Real-Time SystemsLatency ConstraintsMulti-Agent CoordinationAI GuardrailsSpeech AI Pipelines

Tech Stack

Tools & technologies

Python

About the role

Key responsibilities & impact

Build the shared platform layer that makes Kaltura's agentic AI extensible, measurable, and self-improving
Develop the orchestration engine, skills registry, evaluation harness, guardrails system, memory service, integration gateway, and tracing infrastructure
Support both real-time conversational and offline video generation runtimes
Design and build platform systems for planning, sub-agents, parallel execution under deadlines, retrieval, evaluation, tracing, guardrails, integrations, and memory
Create shared machinery that customer-facing teams and customers can extend without bespoke engineering per customer
Own major platform components and integrate them with the real-time pipeline under latency constraints
Enable FDE teams and multiple customers to consume platform components
Deliver foundation components that accelerate customer onboarding and provide actionable diagnostics

Requirements

What you’ll need

4+ years building production backend/platform systems — distributed services, APIs, async processing, and systems that serve multiple consumers
Python as primary language
Experience with high-throughput, low-latency services
Deep hands-on experience with LLMs in production, 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, or tracing systems
Understanding of contracts, versioning, and shipping platforms rather than features
Ability to make build-versus-adopt decisions and integrate open-source tooling into production systems
In-depth experience with RAG systems, including indexing strategies, retrieval evaluation, chunking, re-ranking, hybrid search, and failure modes
Familiarity with vector databases such as Pinecone, Weaviate, Qdrant, or similar, and embedding models
Familiarity with real-time system constraints, latency budgets, deadlines, and streaming architecture
Strong systems design skills
Nice to have: LLM evaluation experience and familiarity with DeepEval, Ragas, or similar
Nice to have: Experience with multi-tenant platforms, tenant isolation, and scoped configuration
Nice to have: Background in speech/multimodal AI pipelines, including ASR, TTS, avatar rendering, or video generation
Nice to have: Platform-level observability and tracing experience; familiarity with Langfuse, Opik, OpenTelemetry, or similar
Nice to have: Familiarity with CrewAI, AutoGen, Semantic Kernel, MCP protocol, and multi-step AI system failure modes
Nice to have: Experience with AI guardrails and safety, including input filtering, output validation, grounding checks, and real-time validation latency trade-offs

Benefits

Comp & perks

Hybrid, flexible work environment
Extended private health (including mental) insurance
Personal and professional development programs
Occasional Cross company long weekends