CareerPlanGet AI match score →

Lead Applied Ai Engineer

💼 Full-time🗓 2026-07-30

Core

Lead AI Engineer owning the AI surface of GPTease, an AI-powered chat platform for content creators, managing agent architecture, evaluation, and vendor strategy.

Role type

Senior IC Applied AI Engineer

Builds

AI-powered chat platform for content creators

Domain

Creator economy / Applied AI

Deliverable

production ML models

Required skills

Agent architecture design, Evaluation infrastructure design, Multi-provider inference routing, System prompt engineering, Memory and retrieval pipeline design, TypeScript/Node fluency

Preferred skills

Vision/multimodal production work, Fine-tuning (LoRA, DPO, IPO), OSS contributions in eval/agent frameworks, Creator economy product experience

Technologies

Next.js 14, TypeScript, Supabase, OpenRouter, Mem0, Qdrant, LoRA, Vercel, AWS Lambda, PostHog, Sentry

Responsibilities

Design agent architecture and AI behavior flows, Build evaluation infrastructure for model comparison and regression testing, Manage multi-provider inference routing and vendor stack, Develop memory, retrieval, and vision pipelines

Seniority

Senior, hands-on IC

Rewrite
## About the Role We're hiring a Lead AI Engineer to own the AI surface of GPTease — an AI-powered chat platform for content creators. This is a senior IC role. You'll partner with our eng lead and product lead to own the AI layer end-to-end, from agent architecture to evaluation to vendor strategy. AI behavior is your primary surface, but we're hiring for engineering judgment over framework depth. This isn't a "wire up another RAG demo" role. RAG isn't the frontier anymore. We want someone who can look at where applied AI is going — agentic systems, eval-driven iteration, fine-tuning where it matters — and figure out which moves are right for our product and our creators. This role is for you if you've already been the most senior AI engineer on a team, have led an AI surface end-to-end, and are comfortable making architectural and product calls without waiting for permission. You'll own: - Agent architecture and the next phases of AI behavior in our product - Evaluation infrastructure — quality metrics, model comparison, regression testing - System prompts and persona behavior across the chat product - Multi-provider inference routing and the AI vendor stack - Memory, retrieval, and vision pipelines ## Must-haves - 5+ years shipping production applied AI / LLM systems, with at least 2 of those as the senior AI engineer on a team - Built or led agent systems — planning, tool use, multi-step reasoning. You've designed agent flows, not just used a framework. - Strong eval design instincts. You've shipped a model or prompt change that moved a metric, not just tried a prompt. - Fluent with multi-provider inference routing and AI vendor evaluation. You've made real cost-versus-quality tradeoffs in production. - Strong TypeScript / Node fluency - Comfortable across the stack when needed (Supabase edge functions, queues, scripting) - Currency in the field. You read papers and release notes because that's how you operate, not because someone asked. ## Bonus Points - Vision / multimodal production work - Fine-tuning experience (LoRA, DPO, IPO) - OSS contributions in eval, agent, or inference frameworks - Production work on a creator-economy product - Familiarity with the 18+ creator economy ## Tech Stack - Next.js 14 (App Router) - TypeScript - Supabase (Postgres + Edge Functions) - OpenRouter - Mem0 - Qdrant - LoRA fine-tuning pipeline - Vercel - AWS Lambda - PostHog - Sentry ## What We Offer - High-ownership role in a growing AI product - Small, fast-moving team, your work ships to real users quickly - Competitive contract rate (India-based)
Sourced via wellfound · Listed on CareerPlan, which tracks 70,000+ jobs from 20+ sources.
Apply on Wellfound ↗