Requirements

7+ years of software engineering experience with recent hands-on work building product features backed by LLMs
Experience with at least one of the following: prompt engineering, LLM evaluation, fine-tuning, or model serving
Strong Python skills and familiarity with APIs/SDKs that handle LLM calls, prompt templates, and structured outputs
Proven track record of shipping user-facing features with attention to latency, tone, and quality of AI output
Comfortable learning new infrastructure tools such as Databricks, AWS, Terraform, and GitHub Actions

Nice to Haves

Experience with LLM evaluation frameworks (judges, graders, calibration methodology) or fine-tuning techniques (LoRA, RLHF/DPO, model distillation)
Prompt optimization frameworks knowledge (e.g., DSPy)
Experience with feature stores or personalization/ranking systems relevant to in-app content recommendations
Background in healthcare, regulated industries, or safety-critical AI systems
Data engineering fundamentals such as Spark, Delta tables, and Parquet

Build and ship LLM-powered product features including AI-generated mobile push notifications, personalized in-app content recommendations, custom user journeys, and conversational AI-powered insights
Improve latency and user experience through streaming, pregeneration, and inference-time tradeoffs while collaborating with product and design teams
Iterate on prompt design and calibration; use fine-tuned health-domain models (Llama, Gemma, MedGemma); maintain safe and high-quality outputs using Judge-as-a-Service
Enable A/B testing for model and prompt changes, using evaluation gates to ensure safe shipping and impact measurement
Contribute to synthetic Q&A generation, golden test sets, and evaluation dataset design for the features being developed
Assist with infrastructure work involving Databricks, AWS (EKS), Terraform, and CI/CD as needed
Collaborate cross-functionally with Product, Security, Analytics, Medical teams, and technology partners like Databricks, Google, OpenAI, Anthropic, and AWS

Competitive salary with annual reviews and performance incentive scheme participation
Paid holiday, sick leave, female health leave, and enhanced parental leave/pay for all parent types
Accelerated professional growth supported by impactful work and learning opportunities
Hybrid working model with 3 days per week in the office and in-person collaboration
5-week fully paid sabbatical at 5-year anniversary
Flo Premium subscription for friends & family plus additional health, pension, and wellbeing perks