Forward Deployed Engineer

Blackstone& are a technical consultancy who specialise in digital transformation and complex technical deliveries. 15 years ago that meant Cloud adoption. 10 years ago it was Dev Ops. 5 years ago, SRE and platform engineering. We still cover all of that, but right now a significant part of our work is AI adoption. And we mean actual AI adoption: in production, in Enterprises.

Not just a vibe coded app on a local machine.

The pace and impact of each wave keeps accelerating, but we think successful adoption still comes down to two things: people and constraints. What does transformation actually look like inside the limits of an organisation, and how do we bring the people along for it?

This engagement is with one of our healthcare clients. Healthcare is one of the most consequential environments you can work in: the data is sensitive, the governance is strict, and the stakes of getting things wrong are real. We are not looking for someone who already knows healthcare inside out. We are looking for an engineer who knows how to work carefully and rigorously in environments where that level of care is non-negotiable.

Interested in helping us answer those questions for our customers?

• Solid back-end engineering foundations. You write code that others can read, test, and build on.
• Hands-on experience with AWS Bedrock, including model invocation, knowledge base integration, and deployment patterns within AWS environments.
• Experience with AWS Agent Core or equivalent agent orchestration tooling on AWS, building agents that are reliable enough for production use.
• A strong grasp of how large language models actually work: their failure modes, their sensitivities, and how to engineer systems around them.
• Proven experience building RAG systems end-to-end: chunking and embedding strategies, retrieval tuning, and grounding outputs in source data.
• The ability to build evaluation harnesses that measure what matters: quality, consistency, regression, and real-world performance.
• Context engineering instincts. You think carefully about what goes into a model's context window and why.
• Prompt writing as an engineering discipline: systematic, tested, version-controlled, and repeatable.
• Comfort working directly with clients in complex, regulated environments with real governance constraints. Healthcare experience is not required; the right mindset is.

• Experience with production agentic systems: multi-step reasoning, tool use, memory, and safe orchestration in high-stakes settings.
• Familiarity with agentic design patterns specific to AWS, including Lambda-backed tools, Step Functions integration, or Bedrock Agents.
• Exposure to fine-tuning or domain adaptation of foundation models.

• Architect and build AI systems on AWS Bedrock and Agent Core, covering RAG pipelines, knowledge bases, agent workflows and production APIs.
• Develop back-end integrations that connect AI capabilities to client platforms securely, at scale, and within the governance requirements of a healthcare setting.
• Own the evaluation layer, designing and running harnesses that give the delivery team and the client confidence in every release.
• Engineer prompts and context strategies that perform consistently in production, not just in testing.

• Partner with delivery managers and architects to shape AI solutions that map to real client outcomes, not just technical possibilities.
• Engage confidently with client stakeholders, translating technical decisions into language that lands in a regulated, risk-aware environment.
• Share knowledge across the Blackstone& team: documentation, architecture decisions, and lessons learned from the field.

• Maintain high engineering standards across everything you produce. Testing, documentation, and code quality are not optional extras.
• Bring new techniques and tools to the team when they are genuinely useful, grounded in evidence rather than novelty.
• Contribute to how Blackstone& builds and delivers AI. This is a practice in growth and your experience shapes it.

This engagement will suit you if you:

• Treat AI engineering as a craft:…