Applied AI Engineer

Mem0 • San Francisco, CA

9d • $150,000 - $250,000 • Onsite

About The Position

Own the 0→1. You’ll turn vague customer use cases into working proofs-of-concept that showcase what Mem0 can do. This means rapid full-stack prototyping, stitching together AI tools, and aggressively experimenting with memory retrieval approaches until the use case works end-to-end. You’ll partner closely with Research and Backend, communicate trade-offs clearly, and hand off winning prototypes that can be hardened for production.

Requirements

• Full-stack fluency: Next.js/React on the front end and Python backends (FastAPI/Django/Flask) or Node where needed.
• Strong Python and TypeScript/JavaScript; comfortable building APIs, wiring data models, and deploying quick demos.
• Hands-on with the LLM/RAG stack: embeddings, vector databases, retrieval strategies, prompt engineering.
• Track record of rapid prototyping: moving from idea → demo in days, not months; clear documentation of results and trade-offs.
• Ability to design small, meaningful evaluations for a use case (quality + latency) and iterate based on evidence.
• Excellent communication with Research and Backend; crisp specs, readable code, and honest status updates.

Nice To Haves

• Model serving/fine-tuning experience (vLLM, LoRA/PEFT) and lightweight batch/async pipelines.
• Deployments on Vercel/serverless, Docker, basic k8s familiarity; CI for demo apps.
• Data visualization and UX polish for compelling demos.
• Prior Forward-Deployed/Solutions/Prototyping role turning customer needs into working software.

Responsibilities

• Build POCs for real use cases: Stand up end-to-end demos (UI + APIs + data) that integrate Mem0 in the customer’s flow.
• Experiment with memory retrieval: Try different embeddings, indexing, hybrid search, re-ranking, chunking/windowing, prompts, and caching to hit task-level quality and latency targets.
• Prototype with Research: Implement paper ideas and new techniques from scratch, compare baselines, and keep what wins.
• Create eval harnesses: Define small gold sets and lightweight metrics to judge POC success; instrument demos with basic telemetry.
• Integrate AI tooling: Combine LLMs, vector DBs, Mem0 SDKs/APIs, and third-party services into coherent workflows.
• Collaborate tightly: Work with Backend on clean contracts and data models; with Research on hypotheses; share learnings and next steps.
• Package & handoff: Write concise docs, scripts, and templates so Engineering can productionize quickly.

What This Job Offers

• Job Type: Full-time
• Career Level: Entry Level
• Education Level: No Education Listed