Director of Innovation Delivery
工作简介：作为创新交付总监，你将构建人工智能原生产品。你将领导跨功能的创新交货队，在网络，移动，人工智能代理和流媒体后台中拥有端到端结果。你是一个实践技术领袖，可以扩展范围，建筑师，员工和运输；然后以安全的方式运行产品。责任：·站起来运行团队 （发现 → 原型 → 产品 → 平台 & SRE）. ·设计和运送 RAG/代理系统：选择模型 （例如 Anthropic Claude,OpenAI,Google 或 Llama / Mistral 等开放权重）,定义工具/函数，并在需要时选择检索 （默认 grants + peave,扩展至 Wviate / PQ / Postcon）· 运行 AI 安全：评估和防护线，结构化输出 (JSON/Schema),PII 编辑，拒绝政策，成本/延迟预算以及 LLM 可观测性。· 自有交付结果：SLO,质量，成本，速度；使用特征旗和加拿大标签发布。· 对客户进行面对应：发现，范围，SoW,路线图，QBRs. ·聘用/教练技术领导者，EM 和 PM;升级实践。要求 · 812年以上的人工智能工程；4+年领先的多组系统；在生产网/移动规模上发送。·至少一个 DB 交付应用程序使用 Claude/GPT/Gemini/Llama/Mistral,支持取回 （pgvalve 或基本向量）和一项评价/导向管道。· 实现的管弦乐器 （长度图/DSPy 或时间流程）,重排器 （例如 Cohere/Jina/Voyage）,并使用提示/工具版本。· 用现代云+数据构建：无服务器/K8s,Terraform,OpenTelemetry,功能标志/实验。·优秀的客户通信和商业感 （SoWs,人员，利用）.技术堆 （你有经验）·模型：Anthropic Claude; OpenAI;Google;开放权力 (Local,Mistral). · Orchestration & Tempy 代理人：图表；可持续的，长期运行的任务和 SLA. ·检索：Postgres + pGray (Qeavity);当与 Wesensector /Search/Discontone 进行扩展时，需要模拟式_template=p =p>Template=drive. · 嵌入/重排：OpenAI/Voyage/E5/BGE;Cohere/Jina/Voyaage 重排。· Guardrails & evals: JSON/Pydantic 方案，红团组集合，promptfoo/Ragas/DeepEval;内容/PII 筛选器。· 可观察性：OpenTelemetry 痕迹包括提示/工具范围；Langfuse/Arize Phoenix （或相等）+ Sentry/Grafana. · App&data: Next.js Type 15 (RSC),Script/Go/Python; Postgres; Kafka/Redpanda/NATS; dbt/lakehouse 可选。· Ops: Run/ECS/K8s; Terrpost
查看英文原文
Job Summary:
As a Director of Innovation Delivery you will build AI-native products. You’ll lead cross-functional Innovation Delivery Squads—owning outcomes end-to-end across web, mobile, AI agents, and streaming backends. You’re a hands-on technical leader who can scope, architect, staff, and ship; then run the product safely at scale.
Responsibilities:
- Stand up and run squads (Discovery → Prototype → Product → Platform & SRE).
- Design and ship RAG/agent systems: pick models (e.g., Anthropic Claude, OpenAI, Google, or open-weights like Llama/Mistral), define tools/functions, and choose retrieval (default Postgres + pgvector, scale to Weaviate/Qdrant/Pinecone when needed).
- Operate AI safely: evals & guardrails, structured outputs (JSON/Schema), PII redaction, refusal policies, cost/latency budgets, and LLM observability.
- Own delivery outcomes: SLOs, quality, cost, velocity; release with feature flags and canaries.
- Be client-facing: discovery, scoping, SoW, roadmap, QBRs.
- Hire/coach Tech Leads, EMs, and PMs; level up practices.
Requirements
- 8–12+ yrs engineering; 4+ yrs leading multi-team delivery; shipped production web/mobile systems at scale.
- Shipped at least one production AI app using Claude/GPT/Gemini/Llama/Mistral, backed by retrieval (pgvector or a vector DB) and a basic eval/guardrail pipeline.
- Implemented orchestration (LangGraph/DSPy or Temporal for durable workflows), rerankers (e.g., Cohere/Jina/Voyage), and prompt/tool versioning.
- Built with modern cloud + data: serverless/K8s, Terraform, OpenTelemetry, feature flags/experimentation.
- Excellent client communication and commercial sense (SoWs, staffing, utilization).
Tech stack (you have hands on experience)
- Models: Anthropic Claude; OpenAI; Google; open-weights (Llama, Mistral).
- Orchestration & agents: LangGraph (or DSPy) for graphs; Temporal for durable, long-running tasks and SLAs.
- Retrieval: Postgres + pgvector (default); Weaviate/Qdrant/Pinecone when scale/ops require; hybrid search with OpenSearch/Typesense.
- Embeddings / rerankers: OpenAI/Voyage/E5/BGE; Cohere/Jina/Voyage rerank.
- Guardrails & evals: JSON/Pydantic schemas, red-team sets, promptfoo/Ragas/DeepEval; content/PII filters.
- Observability: OpenTelemetry traces incl. prompt/tool spans; Langfuse/Arize Phoenix (or equivalent) + Sentry/Grafana.
- App & data: Next.js 15 (RSC), TypeScript/Go/Python; Postgres; Kafka/Redpanda/NATS; dbt/lakehouse optional.
- Ops: Cloud Run/ECS/K8s; Terraform/OpenTofu; GitHub Actions; LaunchDarkly/Unleash; Statsig/GrowthBook.
Originally posted on Himalayas