Chiri

Compensation

Full Description

Full Stack Software Engineer – AI Platform & Applied AI Systems Location: Remote / Americas Type: Full-Time Why Chiri Chiri builds governed AI systems that operate in the real world — not demos, not prototypes, not black boxes. Our platform, Chiri Brain, is a governed AI operating system for humans and agents. It ensures AI systems are transparent, auditable, and secure — from prompt to execution. In addition to our core platform, we design and deploy applied AI systems for clients — AI tools that operate in messy, high-signal, time-sensitive environments. This role spans both. Role Overview We’re hiring a Fullstack Software Engineer to split time between: Platform Development (≈60–70%) Expanding Chiri Brain’s governed AI control plane and orchestration systems. Applied AI Systems (≈30–40%) Designing and shipping real-world AI systems involving data ingestion, scraping, computer vision, and intelligent scoring workflows. You’ll work on systems that: Ingest messy, real-time external data Perform AI-driven classification and similarity detection Aggregate multi-source data into structured signals Expose traceable AI decisions through production APIs and UIs This is not a simple LLM integration role. We build systems that must operate reliably under technical, economic, and governance constraints. Key Responsibilities Platform Development (≈60–70%) Build AI control-plane primitives (personas, policies, traceability, execution logs) Implement auditable inference pipelines Design workflow orchestration for human + agent collaboration Develop RAG pipelines with structured retrieval and citation Support multi-model execution and evaluation frameworks Build secure backend services (Python) and frontend interfaces (TypeScript) Applied AI Systems (≈30–40%) Design and implement scalable data ingestion pipelines Build scraping systems for hard-to-scrape, login-gated, or dynamically rendered sites (e.g., social platforms, marketplaces, auction platforms) Handle rate limits, bot mitigation, anti-automation defenses, and data normalization Implement image embeddings and similarity search pipelines Design scoring or valuation logic that combines multiple data inputs Build internal tools that surface AI reasoning transparently for end users Work directly with stakeholders to iterate quickly on production systems Required Qualifications 3–6 years of fullstack engineering experience with production ownership Strong Python backend experience (FastAPI, Django, or similar) Strong TypeScript frontend experience (React, Vite, or similar) Experience building and maintaining scraping systems for complex or protected sites Experience designing data pipelines and normalization workflows Familiarity with vector databases (PGVector, Pinecone, Weaviate, etc.) Experience working with embeddings (text and/or image) Comfort building systems that combine AI inference with deterministic business logic Strong English communication skills (English C2 for non-native speakers) Preferred Qualifications Experience scraping dynamically rendered sites (e.g., heavily client-side JS frameworks) Experience working with login-gated or bot-protected environments Experience building internal analytics or scoring engines Experience designing real-time or near-real-time systems Exposure to enterprise governance requirements (RBAC, logging, compliance) What We’re Looking For An engineer who: Can move between infrastructure and applied systems Understands that scraping in production is a systems problem, not a script Thinks in terms of signal extraction, not just data collection Can ship fast without sacrificing structure Is comfortable building AI systems that must actually make or influence decisions