Job Description

A strong hands-on developer who executes the build alongside the senior engineer: implementing assistants, RAG pipelines, and integrations to specification and iterating quickly on feedback. Attends daily stand-ups on the US Central pattern and connects with US stakeholders as needed, while the senior engineer fronts the business relationship.

Key Responsibilities

• Develop and maintain LLM-powered assistants and supporting services on the client's platform components.
• Implement RAG pipelines: document ingestion, pre-processing, embedding, index/vector-store creation, retrieval integration and testing.
• Build integrations between assistants, ML model endpoints, data sources, and enterprise systems via APIs and connectors.
• Support model-integration tasks under the senior engineer's direction, including evaluation harnesses and regression checks on assistant behaviour.
• Participate in daily stand-ups and sprint ceremonies; deliver iteratively against a fast-changing, lightly documented backlog.

Must-Have Skills

• Solid Python engineering; REST API development and consumption; JSON/data wrangling; Git workflows.
• Hands-on LLM app development: prompting, assistant configuration, function/tool calling, basic evaluation.
• Practical RAG implementation experience with at least one vector database / embedding stack.
• Working understanding of ML model concepts sufficient to integrate and test predictive models (does not require model-research depth).
• Reliable US Central shift availability for stand-ups and intermittent stakeholder connects; collaborative, feedback-driven working style.

Good-to-Have

• Exposure to forecasting/analytics use cases; commercial or pharma domain familiarity.
• Cloud services (AWS preferred), containerisation basics, CI/CD; automation/orchestration platform exposure (e.g., UiPath).