Senior AI Engineer

Avolution•London, CA

4d•Hybrid

About The Position

We are building a next-generation AI-powered Enterprise Architecture (EA) platform, and we’re looking for a Senior AI Engineer to help define its intelligence layer. This is a unique opportunity to work at the intersection of cutting-edge AI and the complex, high-value domain of enterprise architecture-used daily by architects, CIOs, and business analysts at organisations worldwide. You’ll work closely with our engineering team, product managers, and stakeholders to design and build LLM-powered assistants, intelligent reasoning over enterprise data, and agentic workflows integrated with real enterprise systems. This role combines deep AI architecture expertise, backend engineering, and system integration. You won’t just be building features-you’ll be shaping the technical direction of AI across the entire platform.

Requirements

6+ years in software / ML engineering
Strong Python and hands-on experience building production-grade LLM-based systems (RAG, agents, evaluation)
Experience designing and building multi-step or stateful AI systems (agents, workflows, or pipelines)
Experience with APIs, microservices, cloud platforms (AWS, Azure, or GCP)
Experience defining and applying evaluation approaches for LLM systems (metrics, benchmarking, or testing strategies)
Familiarity with containerization and orchestration (e.g., Docker, Kubernetes)
Strong system design and architecture skills

Nice To Haves

Experience with graph databases or structured data modeling (e.g., knowledge graphs, complex schemas)
Experience designing systems where AI interacts with structured domain models or enterprise data
Experience with enterprise systems or metadata platforms (e.g., EA tools, CMDB, similar)
Experience building agentic orchestration layers (tool use, planning, multi-step reasoning)

Responsibilities

AI Architecture & System Design
Design end-to-end LLM-based systems (RAG, agents, memory, tool use)
Define scalable and reusable AI architecture patterns (prompting, orchestration, evaluation)
Build context-aware AI leveraging structured and unstructured data
Data Modeling & Context Engineering
Design rich data abstractions and context models for enterprise knowledge
Enable AI reasoning over complex enterprise relationships and hierarchies
Design retrieval and reasoning approaches that go beyond vector search, incorporating structure, relationships, and domain semantics
Backend & Distributed Systems
Build scalable AI services and APIs
Design pipelines for real-time and async workflows
Ensure performance, reliability, observability
Integration & AI Ecosystem
Integrate LLM providers, vector DBs, enterprise systems
Build tooling layer for agent interaction
Design and implement agentic workflows (planning, tool use, multi-step reasoning) integrated with enterprise systems
Evaluation & Production Readiness
Define and implement evaluation approaches for LLM systems (quality, grounding, task success)
Implement guardrails, monitoring, and logging
Optimize latency, cost, and system reliability
Collaboration
Work closely with product, engineering, and domain experts to drive delivery of AI capabilities and influence roadmap direction
Own technical design and implementation of key components, contributing to broader system decisions
Proactively share knowledge, raise the bar on engineering quality, and improve team practices