AI Native Engineer

Description

The team builds AI systems that run in production inside large enterprise clients, not demos or pilots that never ship. The company works across every industry, enterprise technology stack and level of organizational complexity.

This role is for someone who has shipped a multi-agent system to production, has owned an eval harness, and has debugged an agent failure in live operation. Demand for this skill set is rising faster than the supply of people who have it.

Through the company you get access to vendor fellowship programmes with the engineering teams at Anthropic, OpenAI, Microsoft and Google, and a direct route into the Forward Deployed Engineer programme.

Responsibilities

• Design, build and ship production agentic systems from start to finish, covering multi-agent orchestration, RAG pipelines, policy-based routing, tool calls, memory handling and lifecycle observability
• Own RAG pipelines, including embeddings, chunking, vector search and context window design, and tune them against measurable quality targets
• Connect several LLM providers (OpenAI, Anthropic, Vertex AI and open-source models) behind one abstraction, with fallback routing and control over tokens, cost and latency
• Run LLMOps in production: eval harnesses with real quality metrics, prompt versioning, observability tools such as LangSmith, Braintrust or similar, and cost and safety monitoring
• Work alongside client engineers on design, prototypes and deployments through workshops, proofs of concept, pair-coding sessions and architecture walkthroughs
• Create reusable patterns, accelerators and playbooks that outlast a single engagement and speed up the next one
• Set metrics for agent accuracy, latency, safety and cost, and explain findings and recommendations to client stakeholders in business terms

Requirements

• 2 to 5 years of software engineering experience in production environments
• At least 1 year designing and deploying agentic AI solutions in production. This requirement is non-negotiable.
• Production-level experience with agentic orchestration frameworks such as LangGraph, CrewAI, AutoGen or an equivalent, not just tutorial work
• Hands-on experience calling LLM APIs (OpenAI, Anthropic, Vertex AI) in production code, including provider abstraction and trade-offs between tokens, latency and cost
• Experience owning RAG pipelines: embeddings, chunking strategy, vector databases and context engineering
• Working knowledge of LLMOps: eval harness design, prompt versioning and production observability
• Solid cloud-native skills across Kubernetes, Docker, microservices, serverless, CI/CD, and IaC with Terraform or Helm
• Strong Python. Java or another backend language is acceptable. Experience debugging and observing systems in production is required.
• Depth of experience counts more than years. A candidate with 3 production agentic systems shipped over 4 years is preferred to a generalist with passive AI exposure.

Conditions

The role is listed for the EU region

Equal opportunity: hiring decisions are made without regard to age, ethnic origin, belief, colour, religion, sex, national origin, ancestry, disability, veteran status, sexual orientation, gender identity or expression, genetic information, marital status, citizenship, or any other characteristic protected by applicable law

Benefits

• Access to vendor fellowship programmes with the engineering teams at Anthropic, OpenAI, Microsoft and Google
• A direct pathway into the Forward Deployed Engineer programme