W2 only
Onsite in DTLA

AI Product Engineering

Scope & Responsibilities

Prototype LLM-powered tools, copilots, and retrieval workflows using APIs, embeddings, and orchestration frameworks
Build full-stack AI features: retrieval logic, prompt pipelines, caching, evaluation, observability
Own the full AI lifecycle—from data prep and experimentation to deployment and monitoring
Evaluate new models (OpenAI, Claude, Gemini, open-source) and quickly test what works
Improve system performance across accuracy, latency, hallucination, and user experience
Translate ambiguous needs into scoped AI features with clear goals and success metrics
Prioritize experiments and features based on impact, feasibility, and data

Experience Required

5+ years software engineering or ML experience, including 3+ years with LLMs, NLP, or applied AI
Proven track record shipping production AI tools or platforms
Strong with Python, LangChain/OpenAI SDK, embeddings, RAG, and vector DBs
Experience optimizing LLM workflows (latency, cost, reliability)
Ability to think from first principles and operate across technical + product domains
Experience with fine-tuning, LoRA, or open-source model hosting (HF, Ollama, BentoML)
Familiarity with agentic design (LangGraph, task decomposition frameworks)
Exposure to product analytics and A/B testing
Experience building internal tools or automation that improved efficiency
Ability to design user flows while optimizing prompts or embedding indexes

Personal Attributes

Someone who thrives on turning the latest LLM and GenAI advances into real, working products—part architect, part engineer, part product hacker. Comfortable taking ideas from concept to prototype to production quickly.

Education

Bachelor’s degree required; Master’s in CS or Data Science preferred.

Kinect AI Jobs

Latest Jobs

AI Engineer