AI Agent Architect — Build Production-Grade Agents

Nacre Capital; España; Remote; EUR 110,000 - 140,000; Full time

Benefits offered by this job

Remote-first

Direct CTO access

Budget for models & tooling

Job summary

EveryWatch is seeking a Senior AI Engineer, Agents to design, build, and scale AI-powered solutions across our data-driven platform. You will own the agent architecture, code the loops and memory, and partner with product, sales, and data teams to turn ideas into production features.

You will ship hands-on, critique architecture, manage cost and latency, and push for measurable quality with golden datasets and verifiers.

Qualifications

• 6+ years shipping production software, of which 2+ on LLM systems that real users touched.
• Real agentic depth: ReAct or equivalent loops, tool/function calling, planners, state & checkpointing, long‑term memory, HITL steps, streaming.
• Hands‑on LangGraph (or a strong argument for something better) plus a tracing/observability stack - LangSmith, Langfuse or similar
• Python in production: FastAPI, async job processing, clean service boundaries
• RAG done properly: retrieval + re‑ranking + relevance judgement, and honest evaluation of all three
• Evaluation as a habit, not an afterthought (RAGAS/DeepEval/GEVAL, LLM-as-judge, pass@k)
• Cloud production experience - AWS (Bedrock, SQS, EC2/EKS, S3) or equivalent - with Docker and CI/CD
• The spine pushes back on us. We explicitly want someone who asks "why did you build it like that?"

Responsibilities

• Invent the agent roadmap. Sit with sales, data and product, find the repetitive expert work, and come back with a ranked list of agents worth building - with a real view on feasibility, cost and impact.
• Build them yourself. You are hands‑on. You design the architecture and you write the code - tools, loops, sub‑agents, memory, state, evaluation.
• Own the platform under the agents. Every new agent should be cheaper to build than the last: shared tool layer over Watch data (pricing, auctions, listings, references, portfolios), an MCP surface over our existing backend, shared memory, tracing, and a reusable eval harness
• Harden WatchChat alongside us. Multi‑turn state and memory, latency, cost, tool‑call reliability, regression gates. It's live‑bound and it has to stay right
• Make quality measurable. Golden multi‑turn datasets, programmatic verifiers for tool/argument correctness, LLM-as-judge on held‑out sets. If we can't measure an agent, we don't ship it
• Treat cost and latency as design constraints. Cheap models for routing and intent, strong models where they earn their keep; context budgets, caching, and - where it pays off - fine‑tuning (SFT/LoRA on curated production trajectories) instead of ever‑larger prompts

Skills

LLM systems

LangGraph

Python in production

Tracing/Observability

AWS (Bedrock)

CI/CD

Tools

LangSmith

Langfuse

Docker

FastAPI

S3

Job description

EveryWatch is seeking a Senior AI Engineer, Agents to design, build, and scale AI-powered solutions across our data-driven platform. You will own the agent architecture, code the loops and memory, and partner with product, sales, and data teams to turn ideas into production features.

You will ship hands-on, critique architecture, manage cost and latency, and push for measurable quality with golden datasets and verifiers.