Apply on Employer Site

Mem0 · 2 days ago

Forward Deployed Engineer

San Francisco, CA

Full-time

Onsite

Mid, Senior Level

$150K/yr - $180K/yr

3+ years exp

Mem0 is building the memory layer for AI agents, enabling long-term memory in AI interactions. They are seeking a Forward Deployed Engineer to own customer integrations, design solutions, and troubleshoot issues while collaborating closely with clients and internal teams.

Artificial Intelligence (AI)Information TechnologyMachine LearningSaaS

Responsibilities

Own onboarding & integration: Plan and deliver deployments, set up environments/keys/tenants, and guide customers through Mem0 SDKs (Python/JS), and REST APIs

Translate needs → solutions: Run technical discovery, define data models and privacy constraints, and design integration architectures that fit the customer’s app

Prototype fast, harden to prod: Build reference implementations/POCs, then productionize with tests, observability, and safe rollout plans

Solve issues in the field: Debug auth/SSO, schema mapping, rate limits, and latency; optimize caches, queries, and memory/retrieval settings for real workloads

Operate with customers: Set SLIs/SLOs, add dashboards and alerts, write runbooks, and handle incident triage through to root cause and fix

Bridge to Product & Eng: Capture structured feedback, file crisp tickets/specs, and influence the roadmap with repeatable patterns from deployments

Enable & educate: Write docs, sample code, and playbooks; run workshops so customer teams can self-serve and scale

Qualification

PythonTypeScript/JavaScriptREST/GraphQL APIsSaaS integrationLLM/RAG conceptsSQL proficiencyCloud familiarityCommunicationHigh ownership

Required

3+ years as a software engineer in customer-facing integration/solutions/forward-deployed roles

Strong coding in Python and TypeScript/JavaScript; comfortable touching Next.js/React frontends and Django/FastAPI/Node backends

Proven experience integrating SaaS platforms: REST/GraphQL APIs, webhooks, auth (OIDC/SAML/JWT), and event flows

Practical knowledge of LLM/RAG concepts and vector databases (e.g., FAISS/Milvus/Pinecone); able to tune retrieval/memory settings for quality and latency

Solid debugging across network/auth/data layers; SQL proficiency and performance profiling basics

Excellent communication with both engineers and non-technical stakeholders; clear docs, clear calls, clear decisions

High ownership: you manage timelines, unblock dependencies, and land successful go-lives