Full-Stack Solutions Engineer

Location: Hybrid(Bristol) | Type: Full-Time/Permanent

About Newpage Solutions

Newpage Solutions is a global digital health innovation company helping people live longer, healthier lives. We partner with life sciences organisations which include, pharmaceutical, biotech and healthcare leaders, to build transformative AI and data driven technologies addressing real-world health challenges.

From strategy and research to UX design and agile development, we deliver and validate impactful solutions using lean, human-centered practices.

We are proud to be a ‘Great Place to Work®’ certified company for the last three consecutive years. We also hold a top Glassdoor rating and are named among the "Top 50 Most Promising Healthcare Solution Providers" by CIOReview. As an organisation, we foster creativity, continuous learning and inclusivity, creating an environment where bold ideas thrive and make a measurable difference in people’s lives.

Your Mission

We're looking for Full-Stack Solutions Engineer who treat AI as the medium they build in, not a tool they're still getting used to.

You'll sit with clients and product leaders, turn vague problems into something concrete and ship working software end-to-end - no waiting for a polished backlog, no PM in the middle, no handoff to a separate platform team. You shape the idea, build it and put it into production yourself.

This is a hands-on, individual-contributor role for engineers working at the sharp edge of AI development - fluent in Claude Code, Cursor, agents, eval harnesses, MCP, and modern TypeScript and Python. We want people who are curious by nature, who like figuring things out in the open and who want to grow the business as much as they grow themselves.

What You’ll Do

Discovery

Work directly with business and clinical leaders to turn loose ideas into buildable solutions

Know what to build by the end of a conversation, and have a working prototype by the end of the week

Demo live, reframe problems out loud and make the call yourself rather than waiting to be told

Lead POCs, innovation sprints and internal experiments that test new AI techniques

Build

Build modular backends in Python or TypeScript using clean architecture, OOP, SOLID and DDD

Ship full-stack apps, APIs, agents and workflows with tools like Next.js, React, FastAPI, Fastify, FastMCP and Hono

Architect production-grade agentic applications with LangGraph, AutoGen, Claude Agent SDK, OpenAI Assistants or your own orchestration layer

Integrate frontier and self-hosted LLMs (Claude, GPT, Gemini, open-weight models) via MCP and custom connectors

Apply RAG where it genuinely earns its place - vector databases, hybrid retrieval, BM25 and similarity search

Work across relational, document, key-value and graph databases as the problem demands

Design prompt and context engineering that balances accuracy, repeatability, cost and latency

Use AI-assisted development - Claude Code, Copilot, Cursor, Codex - through proper structured workflows, not ad hoc prompting

Ship and Own

Build the infrastructure, write the evals, connect the MCP servers, deploy the agents, harden it for real users

Deploy to AWS, Azure, Cloudflare or Vercel via Docker, Kubernetes or serverless

Treat evaluation as a first-class discipline - know where AI tooling helps & where it still falls short

Bring proper engineering practice: TDD, secrets management, security testing, structured logging, tracing, CI/CD

Own what you build end-to-end, including keeping it running

Work with others on system design, agentic patterns and AI engineering practice

What You Bring

3+ years building production applications with AI or agentic approaches - full-stack apps, agents, workflows, MCPs

Real hands-on experience with agents, not just prompting models - wiring tools to models for multi-step execution

Active, structured use of AI-assisted development tools (Claude Code, Cursor, Copilot)

Python or TypeScript, with OOP, SOLID, 12-factor and microservices experience

End-to-end experience with vector databases, retrieval pipelines and evaluation harnesses

Cloud-native deployment – AWS/Azure, Cloudflare/Vercel, with Docker, Kubernetes & GitHub Actions

A genuine no-compromise attitude to clean code, testing, security, observability and cost

A solid understanding of how LLMs actually behave, where they break, and how to tune for accuracy, latency and cost

Clear written communication and the confidence to reframe a problem out loud

Something to show for it - GitHub, a portfolio, side projects, indie tools, open-source work

A builder's mindset and a real appetite for ambiguous, high-impact problems

A Bachelor's in Computer Science, Machine Learning or a related field

Bonus Points

Public writing, talks or threads about building with AI

MLOps and model serving experience (BentoML, MLflow, Vertex AI, SageMaker)

Streaming or batch pipeline experience (Spark, Airflow, Beam, Glue)

Healthcare or life sciences exposure

AWS Professional or other relevant certifications

What We Offer

At Newpage, We’re Building a Company That Works Smart And Grows With Agility, Where Driven Individuals Come Together To Do Work That Matters. We Offer

A people-first culture - Supportive peers, open communication and a strong sense of belonging

Smart, purposeful collaboration - Work with talented colleagues to create technologies that solve meaningful business challenges

Balance that lasts - We respect your time and support a healthy integration of work and life

Room to grow - Opportunities for learning, leadership and career development, shaped around you

Meaningful rewards - Competitive compensation that recognises both contribution and potential