K
Senior AI Engineer
HybridFull-timeAI EngineeringEnterprise SoftwareVideo Technology
Build the shared platform layer that makes agentic AI extensible, measurable, and reliable across real-time conversational and offline video-generation systems. You will develop core infrastructure used by multiple teams and enterprise customers.
Responsibilities
- Design and build the agentic AI orchestration platform
- Develop skills registries, evaluation harnesses, guardrails, integration gateways, memory services, and retrieval infrastructure
- Support planning, sub-agent coordination, parallel execution, tool calling, and deadline-aware processing
- Build shared platform primitives with clear contracts and versioning
- Develop RAG infrastructure, including indexing, retrieval, re-ranking, and embedding workflows
- Integrate platform components with real-time conversational and offline video-generation runtimes
- Implement evaluation, tracing, observability, and regression-detection capabilities
- Design for multi-tenant isolation and customer-specific configuration
- Improve customer onboarding by replacing bespoke integrations with reusable platform capabilities
Requirements
- 4+ years building production backend or platform systems
- Strong Python experience with distributed services, APIs, asynchronous processing, and high-throughput, low-latency systems
- Production experience building LLM infrastructure, including orchestration, tool calling, retrieval pipelines, context management, prompt chaining, and multi-agent coordination
- Proficiency with LangChain, LangGraph, or equivalent orchestration frameworks
- Experience building shared platform primitives such as registries, gateways, evaluation frameworks, or tracing systems
- Experience integrating open-source tools into production and making build-versus-adopt decisions
- Deep experience with RAG systems, including indexing, 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
- Understanding of real-time system constraints, latency budgets, deadlines, and streaming architectures
- Strong systems design skills for platforms serving multiple consumers
Nice to have
- Experience evaluating LLM systems with metrics and test harnesses
- Experience with multi-tenant platforms and tenant isolation
- Background in speech or multimodal AI pipelines, including ASR, TTS, avatar rendering, or video generation
- Platform-level observability and tracing experience
- Familiarity with agentic AI frameworks and MCP
- Experience implementing AI guardrails and safety controls
Benefits
- Hybrid work model
- Flexible work environment
- Opportunities for professional growth