Senior AI Engineer – LLMs & Voice AI Systems

SR2; West of England; Hybrid; GBP 90,000 - 130,000; Full time

Job summary

SR2 in Bristol, UK is seeking an experienced AI engineer to shape and deploy production-grade LLM applications and autonomous agents. You will design orchestration, build prompt frameworks and drive evaluation pipelines while advancing voice AI pipelines and real-time inference.

You will optimise models for reliability, latency and cost, explore RAG and multimodal systems, and mentor fellow engineers as you move solutions from experimental phases to commercial deployment.

Qualifications

• Strong software engineering experience with hands-on production AI/ML delivery.
• Proven expertise in LLMs, NLP or autonomous AI agents.
• Experience building robust, scalable AI applications.
• Understanding of AI orchestration and model integration.
• Ability to solve complex problems and communicate technical decisions clearly.
• Confidence working in an innovative, fast-moving engineering environment.
• Experience with GDPR compliance in AI projects.

Responsibilities

• Designing and deploying production-ready LLM applications and autonomous AI agents.
• Building agent orchestration, prompt engineering and evaluation frameworks.
• Developing voice AI pipelines with speech-to-text, text-to-speech and real-time inference.
• Optimising models for reliability, accuracy, latency and cost.
• Working with emerging AI technologies, including RAG and multimodal systems.
• Shaping technical architecture and mentoring other engineers.
• Taking AI solutions from experimentation through to commercial deployment.

Skills

Production AI/ML delivery

LLMs / NLP / Autonomous AI

Robust, scalable AI apps

AI orchestration & model integration

Problem solving & clear communication

Startup/R&D experience

GDPR compliance knowledge

Voice AI / ASR / TTS

LangChain / LlamaIndex / RAG

Real-time inference optimization

Tools

LangChain

LlamaIndex

Job description

SR2 in Bristol, UK is seeking an experienced AI engineer to shape and deploy production-grade LLM applications and autonomous agents. You will design orchestration, build prompt frameworks and drive evaluation pipelines while advancing voice AI pipelines and real-time inference.

You will optimise models for reliability, latency and cost, explore RAG and multimodal systems, and mentor fellow engineers as you move solutions from experimental phases to commercial deployment.