About

Senior AI Engineer (LLM Systems, Personalization, AWS) Project: AI Personalization Platform Type: Contract (Long-Term Potential) Location: Remote Start: Immediately Experience Level: Expert / Senior We are building an advanced AI-powered personalization and recommendation platform designed for users and b2b clients. The system relies on: • Multi-agent LLM orchestration • Real-time preference inference • Short conversational onboarding • Deep context + memory modeling • White-label partner integrations • AWS-native backend • CRM connectivity (Salesforce, HubSpot, etc.) We need a Senior AI Engineer who can take over from our current AI lead, elevate the architecture, improve system accuracy & latency, and build the core logic for personalized recommendations and contextual responses. This is a hands-on, senior-level engineering role, not just prompt work. ⸻ 1. LLM Agent Development (High Priority) • Build and optimize multi-agent workflows (LangGraph or custom logic) • Improve LLM routing and fallback behavior • Implement deterministic guardrails and safety layers • Optimize multi-step reasoning across different agents ⸻ 2. User Memory & Personalization (Abstracted) • Architect and refine a user memory layer • Improve retrieval accuracy • Help design logic that adapts based on user interactions • Support preference modeling and contextual ⸻ 3. Conversational Intelligence • Improve system’s ability to ask fewer questions while inferring more • Reduce friction in onboarding • Enhance contextual continuity across sessions ⸻ 4. Backend Integration (AWS) • Deploy and optimize LLM-driven workflows on AWS • Work with Postgres (with vector search) and Redis • Improve concurrency, latency, and throughput • Support API layer enhancements (FastAPI preferred) ⸻ 5. CRM & Third-Party Integrations (Abstracted) • Ensure the AI layer integrates cleanly into CRM systems (Salesforce, HubSpot, etc.) • Work with webhooks, APIs, or iFrame-based embeds • Support multi-cloud client environments ⸻ 6. Documentation & Handoff • Clean, structured documentation • Loom walkthroughs when necessary • Engineer-to-engineer clarity for future team expansion ⸻ Required Experience MUST HAVE • 5+ years AI/ML experience • Strong LLM systems architecture experience (not just prompting) • Proven experience with multi-agent or multi-step orchestration • Experience with at least two frontier LLM providers (OpenAI, Anthropic, Grok, etc.) • Strong Python (FastAPI or similar) • AWS experience (Lambda, ECS, RDS/Postgres, Redis, S3) • Experience with embeddings, vector stores, and memory systems NICE TO HAVE • Experience integrating AI into enterprise workflows • Experience with Salesforce/HubSpot integrations • Experience with personalization engines or recommendation systems • Ability to work with ambiguous or evolving requirements • Startup or fast-moving environment experience ⸻ Soft Skills • Communicates clearly and proactively • Able to work independently without hand-holding • Comfortable working with founders, product teams, and designers • Can execute fast without sacrificing quality • Strong architectural judgment • Can translate complex AI concepts into clean, workable systems ⸻ What Success Looks Like After 30–60 days, you will have: • Improved accuracy and consistency of multi-agent outputs • Faster and more predictable performance • Cleaner orchestration and routing logic • Better personalization and contextual memory • Tighter integration with backend + frontend • Clear documentation for ongoing development ⸻ Why This Project Is Attractive • Cutting-edge AI work beyond basic chatbots • High level of ownership and autonomy • Opportunity to lead architecture decisions • Direct impact on a premium user experience • Long-term role if performance is strong How to Apply Please submit: • Your experience with multi-agent or LLM orchestration • Your AI architecture experience • Links to relevant repos or portfolio (if available) • Brief explanation of the most complex AI system you’ve built • Your availability and hourly rate