Principal Software Engineer

Trust In SODA; Greater London; Hybrid; GBP 120,000 - 180,000; Full time

Job summary

Trust In SODA is seeking a hands-on Principal Software Engineer to lead GenAI capability design and delivery across our platforms in the biotech space. You will collaborate with data scientists, bioinformaticians, and domain experts to solve real drug discovery and clinical development problems.

You will own production-grade architectures from PoC to general release, setting engineering standards for GenAI/LLM apps and mentoring engineers across the department.

Qualifications

• Proven track record building and operating LLM-powered systems in production (RAG, summarisation, Q&A over enterprise data).
• Experience with AI-ready data foundations (unstructured pipelines, metadata enrichment, vector stores alongside relational databases).
• Strong instincts for production trade-offs: monitoring drift, cost, latency, and reliability at scale.

Responsibilities

• Design and productionise scalable GenAI solutions (RAG, MCP-style integrations, selective agentic patterns).
• Translate complex scientific and business problems into robust, well-integrated AI system designs.
• Set the engineering bar for GenAI/LLM applications.
• Mentor engineers and shape architectural direction across the department.

Skills

LLM production experience

AI data foundations

Observability & reliability

Model versioning & feature flags

Tools

Databricks

AWS

Workflow automation

Job description

We've partnered with a global software leader, providing cloud-based platforms that help the world’s top BioPharma companies manage complex data. We're looking for a hands-on Principal Software Engineer to lead the design and delivery of production-grade GenAI capabilities across their platforms.

This is a technical leadership role: you'll take GenAI solutions from proof-of-concept through early adoption to general release, working closely with data scientists, bioinformaticians, and domain experts to solve real problems in drug discovery, clinical development, and commercial operations.

Day to day:

• Design and productionise scalable GenAI solutions (RAG, MCP-style integrations, selective agentic patterns)
• Translate complex scientific and business problems into robust, well-integrated AI system designs
• Set the engineering bar for GenAI/LLM applications
• Mentor engineers and shape architectural direction across the department

What you'll bring

• Track record building and operating LLM-powered systems in production (RAG, summarisation, Q&A over enterprise data)
• Experience with AI-ready data foundations (unstructured pipelines, metadata enrichment, vector stores alongside relational databases)
• Strong instincts for production trade-offs: monitoring drift, cost, latency, and reliability at scale
• Experience with prompt/model versioning, feature flags, and controlled rollouts

Big plus if you also have:

• GenAI experience in life sciences, biopharma, or other regulated environments
• Familiarity with Databricks, AWS, and enterprise knowledge/workflow automation
• A hand in shaping org-wide AI engineering best practices