Senior / Principal Applied AI Engineer (UK / Europe, Remote)

Explicitly rejects 'vibe coding'—requires writing production code and building agent systems and integrations.

About the Role

Build and ship production-grade AI agents, agentic workflows, and LLM integrations for internal automation and in-product features for a web-native trading platform. Own implementation, observability, and security while partnering with Product and Platform teams to deliver measurable AI systems in production.

Job Description

Role

Senior/Principal Applied AI Engineer responsible for designing, building, and operating production AI agents, agentic workflows, and the orchestration/harness layers that integrate LLMs into internal systems and the trading product. This is a hands-on engineering role: you will write production code, put evaluation and observability on everything shipped, and operate autonomously in a lean team.

Key Responsibilities

• Build agent loops, tool-calling, structured outputs, planning/state management, retries, guardrails, and orchestration layers on top of LLM provider APIs (Anthropic, OpenAI, open-weight models, MCP).
• Ship internal AI automations to remove engineering/support/growth toil by integrating with existing tooling (GitHub, Slack, Intercom, Jira) or building bespoke solutions when required.
• Prototype and productionize in-product AI capabilities for the trading terminal and developer experience, collaborating closely with Product and Core Platform Engineering.
• Make buy-vs-build decisions and integrate or replace third-party platforms where appropriate to deliver outcomes.
• Implement evaluation, observability, and cost/latency guardrails (golden datasets, eval harnesses, tracing, fallback chains, spend controls).
• Operate within security and AI governance constraints (SOC 2 / ISO, approved-tooling allowlist) and handle source/customer/product data responsibly.

Requirements

Must-haves

• 8+ years of production software engineering experience with deep expertise in APIs, integrations, REST, webhooks, OAuth, event-driven and distributed systems.
• 2–3+ years building and shipping production LLM/agent systems from scratch against provider APIs, including writing agent loops, orchestration/harness, tool-calling, guardrails and RAG.
• Hands-on fluency in Python and TypeScript and ownership of production code (this is not a no-code/low-code or advisory role).
• Strong evaluation and observability practices (golden datasets, eval harnesses, tracing, graceful failure modes, cost/latency controls).
• Deep LLM-API fluency (Anthropic/OpenAI/open-weight), MCP, agent frameworks, and familiarity with AI coding tools (Claude Code, Cursor).
• Cloud and delivery experience: AWS and/or DigitalOcean, Docker, CI/CD, SQL/Postgres.
• Strong buy-vs-build judgment and security/data-governance maturity.
• High autonomy and experience operating in lean teams.
• Located in EU/UK timezones with solid overlap with Central European hours.

Nice-to-haves

• Fintech/trading/market-data domain experience or experience as a trading-platform user.
• Open-source contributions to AI tooling (LangChain, LlamaIndex, vLLM, DSPy, or similar).
• Production RAG and vector-database experience; experience with code-generation, transpilation, or developer-experience tooling.

Logistics

• Location: Europe (EU/UK) — fully remote; must overlap Central European working hours.
• Employment type: Full-Time (via Employer-of-Record in your home country).
• Travel: Light, occasional team/leadership meetups.

Skills

System Design API Integration Distributed Systems Agent Design Observability Evaluation & Metrics Security & Data Governance Cloud Infrastructure CI/CD Autonomous Execution Buy-vs-Build Decision Making Product Collaboration

Experience Level

Employment Type

Full Time

• Fully Remote (Europe EU/UK)
• Employment via Employer-of-Record in your home country
• Occasional team/leadership meetups (light travel)

#J-18808-Ljbffr

Full job description from WhatJobs. Apply for this role →