AI Native SW Engineering Specialist

Salary: £50,000 - 75,000 per year

Requirements:

• We require 5+ years of software engineering experience in production environments.
• We require at least 1 year of hands-on experience designing and deploying agentic AI solutions in production.
• We require demonstrated production-depth experience with agentic orchestration frameworks such as LangGraph, CrewAI, AutoGen, or equivalent.
• We require direct production experience calling LLM APIs such as OpenAI, Anthropic, or Vertex AI, including provider abstraction, token management, and latency/cost tradeoffs.
• We require ownership of RAG pipelines, including embeddings, chunking strategy, vector databases, and context engineering.
• We require LLMOps fundamentals, including eval harness design, prompt versioning, and production observability.
• We require cloud-native engineering experience with Kubernetes, Docker, microservices, serverless, CI/CD, and IaC such as Terraform or Helm.
• We require strong Python skills; Java or an equivalent backend language is acceptable.
• We require production debugging and observability experience.
• We prefer candidates who have shipped multiple production agentic systems, with quality of experience weighted over years.

Responsibilities:

• We design and build production-grade agentic systems end to end, including multi-agent orchestration, RAG pipelines, policy-based routing, tool invocation, memory management, and lifecycle observability.
• We build and own RAG pipelines, including embeddings, chunking strategy, vector search, context window engineering, and tuning against real quality targets.
• We integrate and abstract across multiple LLM providers, including OpenAI, Anthropic, Vertex AI, and open-source models, with fallback routing and token, cost, and latency management.
• We implement LLMOps in production, including eval harnesses with real quality metrics, prompt versioning, observability tooling, and cost and safety monitoring.
• We embed directly with client engineering teams to design, prototype, and deploy agentic solutions through workshops, proofs of concept, code-with sessions, and architecture walkthroughs.
• We build reusable patterns, accelerators, and playbooks that scale beyond individual client engagements.
• We define and use metrics to measure agent accuracy, latency, safety, and cost-effectiveness, and present findings and recommendations to client stakeholders in business terms.

Technologies:

• Agentic AI
• AI
• Backend
• CI/CD
• Cloud
• Docker
• Helm
• Java
• Kubernetes
• LLM
• Python
• RAG
• Serverless
• Terraform
• microservices

More:

We are Accenture, a leading global professional services company helping the worlds leading businesses, governments, and organizations build their digital core, optimize operations, accelerate revenue growth, and enhance citizen services. We are a talent- and innovation-led company with approximately 791,000 people serving clients in more than 120 countries. Technology is at the core of our work, and we combine strengths in cloud, data, and AI with deep industry experience, functional expertise, and global delivery capability. This is a full-time role based in London. We also offer broad exposure across industries and enterprise technology stacks, access to vendor fellowships inside Anthropic, OpenAI, Microsoft, and Google engineering teams, and a pathway to the Forward Deployed Engineer programme. We are committed to equal employment opportunity and value the diversity that helps us better serve our clients and communities.

last updated 34 week of 2026