AI Solutions Engineer

Camstgroup; Manchester; On-site; GBP 60,000 - 80,000; Full time

Job summary

A leading technology firm in Manchester seeks an AI Solutions Engineer to lead the design and delivery of bespoke AI applications using OpenAI technologies. The successful candidate will require a deep understanding of full-stack engineering and agentic architectures. Key responsibilities include building production-grade AI systems, leading delivery projects, and ensuring reliability in client engagements. The ideal candidate will have extensive experience with Python, data science tools, and cloud engineering, fostering innovation in applied AI solutions.

Qualifications

• Expert-level Python skills with full-stack engineering background.
• Experience with data science and deep learning tools.
• Proven hands-on delivery of applied AI systems in production.

Responsibilities

• Design and build bespoke AI applications.
• Lead the delivery of AI products with quality assurance.
• Evaluate LLM vendors and tooling at an architectural level.

Skills

Expert-level Python skills

Full-stack engineering background

Experience with data science tools

Deep understanding of software design patterns

Experience with Generative AI

Cloud engineering expertise with AWS/Azure

Experience with OpenAI APIs

Tools

React

TypeScript

Pandas

NumPy

scikit-learn

PyTorch

TensorFlow

Job description

Career Opportunities: AI Solutions Engineer (11010)

Requisition ID11010-Posted - Years of Experience (2) -Technology- Where (1)

Cognita Reply is the vertical setup within Reply that brings OpenAI's AI into clients' day-to-day processes - where change is measured by efficiency, innovation, and ROI. We emphasize partnership, compliance and security, deep sector knowledge, and speed of execution. We deliver scalable, governed, and measurable solutions, integrated with the systems that keep companies running.

Role Overview:

As an AI Solutions Engineer, you will operate at the forefront of applied AI and require deep technical expertise in agentic architectures and full-stack engineering. You will be a hands-on engineer and architect, responsible for designing, building, and delivering end-to-end AI systems, while also serving as a technical leader and delivery owner throughout client engagements. Your work will be engineering-led, focusing on agentic AI systems, bespoke applications, and pioneering new products using OpenAI technologies, all while applying strong architectural judgment and leveraging your broad knowledge of the LLM ecosystem.

Responsibilities:

• Design and build bespoke AI applications using OpenAI models as core backend technology, integrated with traditional software and enterprise systems.
• Architect and implement agentic AI systems, including multi-agent architectures, tool-calling, workflow-driven agents, stateful processes, and human-in-the-loop patterns.
• Build production-grade GenAI systems with robust prompt design, RAG pipelines, LLM evaluation frameworks, and system observability and monitoring.
• Own end-to-end system architecture, covering API/service design, data pipelines, model integration, security, scalability, and cost optimisation.
• Lead the 0–1 delivery of AI products, ensuring technical design, code quality, maintainability, CI/CD pipelines, and cloud deployment.
• Apply deep expertise in OpenAI APIs, focusing on model selection, capability trade-offs, token usage, latency, and enterprise readiness.
• Ensure safety, reliability, and adherence to best practices for OpenAI-based production solutions.
• Evaluate and compare LLM vendors and tooling at an architectural level, while delivering solutions exclusively on OpenAI technologies in line with partnership agreements.

About the Candidate:

• Expert-level Python skills with a strong full-stack engineering background, including frontend (React, TypeScript) and backend API/service-oriented architecture design.
• Extensive experience with data science and deep learning tools such as Pandas, NumPy, scikit-learn, and at least one deep learning framework (e.g., PyTorch or TensorFlow).
• Deep understanding of software design patterns, clean architecture, and developing maintainable, testable codebases.
• Proven, hands-on delivery of applied AI systems in production, including LLM-based applications, agentic frameworks, RAG systems, and evaluation/testing strategies.
• Significant experience with Generative AI, including chat applications, workflow automation, and AI-augmented tools, as well as a strong grasp of LLM system design constraints.
• Advanced cloud engineering expertise with AWS and/or Azure, containerization, cloud-native deployment, and integrating AI workloads into enterprise environments.
• Hands-on experience with OpenAI APIs and best practices, including prompt engineering, tool calling, model configuration, and enterprise deployment considerations.
• Demonstrated ability to lead client projects, mentor teams, translate complex requirements into scalable solutions, and deliver clear technical documentation and communication.

Reply is an Equal Opportunities Employer and committed to embracing diversity in the workplace. We provide equal employment opportunities to all employees and applicants for employment and prohibits discrimination and harassment of any type regardless of age, sexual orientation, gender, identity, pregnancy, religion, nationality, ethnic origin, disability, medical history, skincolour, marital status or parental status or any other characteristic protected by the Law.

Reply is committed to making sure that our selection methods are fair to everyone. To help you during the recruitment process, please let us know of any Reasonable Adjustments you may need.