Senior AI Engineer

Peaple Talent Ltd; West of England; Sur place; GBP 90 000 - 130 000; Plein temps

Résumé du poste

Peaple Talent Ltd is partnering with a fast-growing AI business to recruit a Senior AI Engineer responsible for designing and building production-grade AI systems, spanning LLM orchestration, prompt design, and model integration.

You'll help shape the technical direction, move from research to deployment, mentor engineers, and work across experimentation and production delivery in a fast-paced startup environment.

Qualifications

• Hands-on experience building production AI/ML systems.
• Experience with LLMs, NLP or autonomous agents.
• Strong prompt engineering and agent orchestration skills.
• Experience balancing latency, cost and accuracy in production.

Responsabilités

• Design and build AI systems from research to production.
• Work on LLM orchestration, prompt and agent design.
• Evaluate and benchmark AI systems.
• Collaborate on technical direction and architecture decisions.
• Mentor engineers and contribute to engineering culture.

Connaissances

AI/ML systems

LLMs

NLP

Prompt engineering

Agent orchestration

Model integration

AI evaluation

Software engineering

Production delivery

Formation

PhD or equivalent research experience

Outils

LangChain

LlamaIndex

Description du poste

Peaple Talent is partnering with a fast-growing AI business. They're now looking for a Senior AI Engineer to help design and build the AI systems.

This is a highly hands-on role where you'll work across LLM orchestration, prompt and agent design, model integration, evaluation and voice AI. You'll have the opportunity to work from research and experimentation through to deploying reliable, production-grade AI systems, while helping shape the technical direction of the platform as the team grows.

What You'll Bring:

• Strong hands-on experience building and productionising AI/ML systems
• Practical experience with LLMs, NLP and/or autonomous agent systems
• Strong experience with prompt engineering, agent orchestration and AI evaluation
• Experience integrating and optimising LLMs for production environments, balancing latency, cost and accuracy
• Experience building or improving AI evaluation and benchmarking frameworks
• Strong software engineering background with the ability to turn ambiguous product problems into robust technical solutions
• Comfortable working across experimentation and production delivery
• Strong communication skills, with the ability to explain complex AI concepts to both technical and non-technical audiences
• Experience mentoring engineers and contributing to technical direction and architecture decisions

Nice to Have:

• 5+ years' software engineering experience, including 2+ years working directly with LLMs/NLP in production
• Experience with LangChain, LlamaIndex or similar LLM orchestration frameworks
• Experience designing and implementing RAG architectures
• Experience with voice AI, ASR/TTS or multimodal systems
• Understanding of AI compliance considerations, including GDPR
• Experience working within a startup or fast-paced commercial R&D environment
• PhD or equivalent research experience

If you're an experienced AI Engineer who wants to work on genuinely production-focused AI, autonomous agents and voice technology, this could be a great opportunity to have a real impact as the platform scales.