AI Engineer

hace 2 días

Barcelona, Barcelona, España Quadrivia AI A tiempo completo

The Role

Own and evolve the core "brain" service that powers Qu. Design, build, and operate multi-agent LLM systems that communicate in real time over text and voice. Ship fast Python services with FastAPI, keep latency low, quality high, and evaluation continuous.

What You'll Do

  • 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. WebRTC, SIP, and LiveKit experience is a strong plus.
  • 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.

Minimum Qualifications

  • 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.

Nice To Have

  • DSPy for compilation and self-improving workflows; MiPRO/GEPA integration.
  • Experience with evaluation tooling and LLM-as-judge setups.
  • WebRTC/SRTP, jitter buffers, SIP basics; LiveKit a plus.
  • LiveKit Agents, SIP–WebRTC gateways, TURN/SFU tuning.
  • GCP: Cloud Run/GKE, Pub/Sub, Vertex AI, GCS, Secret Manager, Cloud Logging/Trace.
  • Healthcare data familiarity.

Example Problems You'll Tackle

  • Push median voice round-trip under 2 seconds while preserving turn-taking and barge-in.
  • Set up OTEL-first tracing for the agent graph with automated eval triggers on production traffic slices.
  • Improve our RAG pipeline with hybrid retrieval and re-ranking, then prove gains via faithfulness and context metrics with regression harnesses.
  • Turn EHR integrations into LLM tools.

Tech Stack

Python, FastAPI, pydantic, asyncio, Redis, Postgres, vector stores, WebRTC stacks, LiveKit, SIP gateways, STT/TTS, Docker, Terraform, K8s, OTEL, DeepEval.

What You Get

  • Work on cutting-edge real-time agent tech with a best-in-class team in healthtech.
  • Fun off-sites in Barcelona.
  • High-tech laptop and solid dev ergonomics.
  • Flexibility: work from home or hybrid in Barcelona/London.

  • AI Automation Consultant

    hace 7 días

    Barcelona, Barcelona, España Maisa AI A tiempo completo

    AI Automation Consultant Location: Valencia / Madrid / Barcelona - Spain / Europe - Remote or HybridTeam: Client ServicesWelcome to Maisa - Making AI AccountableOur agentic process automation platform helps enterprises automate complex, decision-heavy processes that traditional automation can't handle and GenAI can't be trusted with. We enable...

  • Software Engineer

    hace 7 días

    Barcelona, Barcelona, España Maisa AI A tiempo completo

    Software Engineer - BackendLocation: Spain/ Europe- RemoteTeam: EngineeringWelcome to Maisa - Making AI AccountableOur agentic process automation platform helps enterprises automate complex, decision-heavy processes that traditional automation can't handle and GenAI can't be trusted with. We enable organizations to scale operations, resist hallucinations,...

  • AI Platform Engineer

    hace 2 semanas

    Barcelona, Barcelona, España Infoplus Technologies UK Limited A tiempo completo

    · Job Title: AI Platform Engineer (Data, Infrastructure & Agentic Systems)· Location: Barcelona, Spain (Hybrid, 2-3 days onsite)· Duration: 6 months (B2B) contractJob Description:Mandatory: Agentic AIKey Responsibilities• Engineer robust data and cloud foundations to support AI workloads and automation at scale across AWS environments.• Design and...

  • AI Platform Engineer

    hace 2 semanas

    Barcelona, Barcelona, España Ubique Systems A tiempo completo

    Role: AI Platform Engineer (Data, Infrastructure & Agentic Systems)Location: Barcelona, Spain6 months extendable contractMandatory:agentic AIKey ResponsibilitiesEngineer robust data and cloud foundations to support AI workloads and automation at scale across AWS environments.Design and implement agentic AI systems as part of a broader automation...

  • AI Platform Engineer

    hace 5 días

    Barcelona, Barcelona, España E-Solutions A tiempo completo

    Role: AI Platform Engineer (Data, Infrastructure & Agentic Systems)Location: Barcelona, Spain6 months extendable contractRate: Euro 300 MAXXMandatory:agentic AIKey ResponsibilitiesEngineer robust data and cloud foundations to support AI workloads and automation at scale across AWS environments.Design and implement agentic AI systems as part of a broader...

  • GTM AI Solutions Engineer

    hace 2 semanas

    Barcelona, Barcelona, España Fynity A tiempo completo

    GTM AI Solutions Engineer - Barcelona (On-site)Are you an engineer who loves tobuild things that drive revenue,not just code for the sake of it?We're supporting afast-scaling SaaS company (1,000+ people, global presence)that's building an internalAI Engineering teamfocused onGTM productivity and revenue generation.Unlike most RevOps teams that buy tools,...

  • AI Data Engineer

    hace 5 días

    Barcelona, Barcelona, España Zurich Insurance A tiempo completo

    We Are Waiting for YouHi thereI am Laura, the recruiter for this position. Nice to meet youFirst, a little bit about what I like the most about working atZurich Technology Delivery Center: The environment here is incredibly collaborative and innovative. Our tech-driven mindset fosters continuous learning and growth, creating an atmosphere where everyone can...

  • AI Platform Engineer

    hace 2 semanas

    Barcelona, Barcelona, España Infoplus Technologies UK Limited A tiempo completo

    Role: AI Platform Engineer(Data, Infrastructure & Agentic Systems)Location: Barcelona, SpainType: Contract PositionPlease find below JD:Strong software engineering background with Python, TypeScript , or similar languages.Proven experience building and automating cloud infrastructure using AWS (EC2, IAM, S3, Lambda, CloudWatch, etc.) and ...

  • AI Principal Engineer

    hace 3 días

    Barcelona, Barcelona, España Checkatrade A tiempo completo

    Join us as an AI Principal EngineerWant to do work that really matters?At Checkatrade, we're building the UK's go-to home improvement marketplace. Every day, we help millions of homeowners find the right tradesperson for the job, fast, fair, and without the faff.AI is a core part of that mission. We believe AI can genuinely improve lives and livelihoods —...

  • AI Engineer

    hace 2 semanas

    Barcelona, Barcelona, España SmartAssets A tiempo completo

    SmartAssets is on the lookout for an experienced and innovative Lead AI Engineer to join our dynamic team. In this role, you will take a leadership position in developing and optimizing AI-driven features, guiding junior engineers, and ensuring the robustness and scalability of our AI solutions. You will play a pivotal role in shaping our platform's future...