AI Engineer

Job not on LinkedIn

October 22

Apply Now

Receive Emails with Similar Jobs

Quadrivia AI

WebsiteLinkedInAll Job Openings

Artificial Intelligence • SaaS • B2B

Quadrivia AI is a healthcare-focused AI company that builds “Qu,” a clinician-facing AI assistant designed to support clinical workflows across providers, payors, pharma and startups. Qu performs tasks such as history-taking, hypothesis generation, investigation recommendations, treatment planning, monitoring, care coordination, and consultation summarization; it maintains a personal health record, is designed for EHR and wearable integration (future capabilities), and emphasizes clinical safety, human-in-the-loop oversight, regulatory compliance, and customizable deployment. The platform is delivered as a cloud-based, customizable product to help clinicians and healthcare organizations scale patient outreach, follow-up, and routine clinical tasks while preserving clinician control and clinical accuracy.

11 - 50 employees

🤖 Artificial Intelligence

☁️ SaaS

🤝 B2B

📋 Description

• Own Qu’s brain service end to end: architecture, SLAs, latency budgets, error modes, rollouts. • Low-latency comms: streaming text and voice, VAD, barge-in, turn-taking, interruption handling. • Multi-agent orchestration: planner–executor–critic patterns, role routing, shared memory, tool routers, coordination protocols and evaluation. • Reasoning & optimization: ReAct, Chain-of-Thought, plus Tree-/Graph-of-Thoughts when useful. • Programmatic prompt optimization: DSPy for prompt/program compilation; integrate MiPRO and GEPA for iterative prompt evolution under eval constraints. • RAG engineering: high-signal retrieval (chunking, hybrid search, re-ranking), query rewriting, compression, caching, freshness, and strong grounding; evaluate faithfulness, context precision/recall, and answer relevancy. • Evaluation & observability: Pre-call validate inputs, enforce safety, and verify retrieval quality for RAG; in-call trace prompts, tool calls, token/latency/cost and enforce streaming guardrails; post-call run automated task evals (faithfulness, relevancy, hallucination, safety), regressions, red-teaming, and CI/CD gates. Instrument with structured logs and OpenTelemetry, surface dashboards and alerts, and feed live traffic slices into shadow evals for drift detection.

🎯 Requirements

• 5+ years in ML or backend engineering in product environments; recent focus on LLM systems. • Expert Python. Strong FastAPI, asyncio, pydantic, and production observability. • Real-time systems: you’ve built or integrated low-latency text/voice. You have used LiveKit, Pipecat or similar tech. • Working knowledge of agent patterns and eval-driven development. • Hands-on with ReAct and CoT; pragmatic with ToT/GoT tradeoffs. • Prior startup experience.

🏖️ Benefits

• Fun off-sites in Barcelona. • High-tech laptop and solid dev ergonomics. • Flexibility: work from home or hybrid in Barcelona/London.