AI Engineer
New
Q
QuadriviaHealth Technology
Flexibility: work from home or hybrid in Barcelona/London.Full-TimeSenior
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Experience
- 5+ years
- Required Skills
- PythonFastAPIWebRTCLLM
Requirements
- 5+ years in ML or backend engineering in product environments
- Recent focus on LLM systems
- Expert level Python proficiency
- Strong experience with FastAPI, asyncio, pydantic, and production observability
- Experience building or integrating low-latency text/voice systems
- Proficiency with LiveKit, Pipecat, or similar technologies
- Working knowledge of agent patterns and eval-driven development
- Hands-on experience with ReAct and CoT
- Prior startup experience
Responsibilities
- Own Qu’s brain service end to end: architecture, SLAs, latency budgets, error modes, rollouts.
- Develop low-latency communications including streaming text and voice, VAD, barge-in, and turn-taking.
- Orchestrate multi-agent systems using planner–executor–critic patterns and tool routers.
- Perform reasoning and optimization using ReAct, Chain-of-Thought, and Tree-/Graph-of-Thoughts.
- Implement programmatic prompt optimization using DSPy, MiPRO, and GEPA.
- Engineer RAG pipelines including retrieval, re-ranking, query rewriting, and grounding evaluation.
- Manage end-to-end evaluation and observability including pre-call validation, in-call tracing, and post-call automated evals.
View Full Description & ApplyYou'll be redirected to the employer's site
