AI Architect
Creative Chaos
Job description
About the role
Creative Chaos is looking for an AI Architect to design and deliver AI‑native products across web, mobile, AI agents and streaming back‑ends. You will lead cross‑functional Innovation Delivery Squads from discovery through to production and platform operations.
Key responsibilities
- Stand up and run squads through Discovery, Prototype, Product and Platform & SRE phases.
- Design, build and ship Retrieval‑Augmented Generation (RAG) or agent systems, selecting models (Claude, OpenAI, Google, Llama, Mistral) and appropriate vector stores (Postgres + pgvector, Weaviate, Qdrant, Pinecone).
- Implement safety mechanisms: evals, guardrails, JSON/schema outputs, PII redaction, refusal policies, cost/latency budgets and LLM observability.
- Own delivery outcomes – SLOs, quality, cost, velocity – and release with feature flags and canary deployments.
- Engage with clients for discovery, scoping, statements of work, road‑maps and quarterly business reviews.
- Hire, coach and level‑up Tech Leads, Engineering Managers and Product Managers.
Required profile
- 8–12+ years of engineering experience with 4+ years leading multi‑team delivery.
- Delivered production web/mobile systems at scale.
- Shipped at least one production AI application using Claude, GPT, Gemini, Llama or Mistral with retrieval and a basic eval/guardrail pipeline.
- Experience with orchestration frameworks such as LangGraph, DSPy or Temporal, and with rerankers (Cohere, Jina, Voyage).
- Strong client communication and commercial sense (statements of work, staffing, utilization).
Required skills
- AI models: Anthropic Claude, OpenAI, Google, Llama, Mistral.
- Orchestration & agents: LangGraph, DSPy, Temporal.
- Retrieval: Postgres + pgvector, Weaviate, Qdrant, Pinecone, OpenSearch, Typesense.
- Embeddings / rerankers: OpenAI, Voyage, E5, BGE, Cohere, Jina.
- Guardrails & evals: JSON/Pydantic schemas, promptfoo, Ragas, DeepEval.
- Observability: OpenTelemetry, Langfuse, Arize Phoenix, Sentry, Grafana.
- Application stack: Next.js 15 (RSC), TypeScript, Go, Python, Kafka, Redpanda, NATS, dbt.
- Operations: Cloud Run, ECS, Kubernetes, Terraform/OpenTofu, GitHub Actions, LaunchDarkly, Unleash, Statsig, GrowthBook.
Questions fréquentes
Why are you reporting this job?
Explore further
Salaries, guides and searches in Pakistan.
Apply in 30 seconds
Enter your email to apply. An account will be created automatically.
By continuing, you accept our terms of use.
Already have an account? Login
A question about this job?
Ask it here: you will get the full job summary by e-mail, right away.
Published 1 day ago
Expires 1 month from now
3 views · 0 interested
Boost your chances
Upload your CV — we will match you with relevant openings.
Analyzing your CV...
Creative Chaos