Applied AI engineer in insurance

Pacific Life; Greater London; Sur place; GBP 90 000 - 150 000; Plein temps

Avantages offerts par ce poste

Competitive salary and bonus schemes

Hybrid working

Private medical insurance

Group life insurance (9x salary)

Group income protection (75%)

Optical benefits

Subsidized gym membership

Cycle to work

Résumé du poste

Pacific Life в составе команды ищет старшего инженера по применению ИИ для разработки и развёртывания сложных LLM‑основанных систем. Вы будете проектировать и внедрять агентские решения для извлечения и рассуждений над данными, работать с межфункциональной командой и ускорять ценностный цикл продукта.

Требуется 6+ лет в ML/AI, глубокие знания NLP/LLM, опыт работы с OpenAI и Anthropic, умение строить оценочные конвейеры и настраивать промты.

Qualifications

• 6+ лет в ML/AI с фокусом на NLP/LLM.
• Практический опыт работы с моделями/ API OpenAI и Anthropic.
• Опыт создания конвейеров оценки для вывода LLM/агентов.

Responsabilités

• Проектирование, сборка и развёртывание систем на базе LLM/агентов для извлечения и рассуждений над данными.
• Разработка и поддержка конвейера оценки и «guardrails»; тестирование гипотез по реальной обратной связи.
• Сотрудничество с продуктом, дизайном и SME‑в контексте доменных ограничений; оптимизация задержек и затрат.

Connaissances

NLP & LLMs экспертиза

Few-shot обучение

Chain-of-thought prompting

Python программирование

Асинхронная архитектура

Итерирование/быстрая сборка

Outils

OpenAI API

Anthropic API

LiteLLM

vLLM

Langfuse

Docker

Kubernetes

FastAPI

PostgreSQL

PyTorch

TensorFlow

AWS

Description du poste

Описание

As a Senior Applied AI Engineer, you’ll take ownership of designing, building, and deploying advanced LLM-based and agentic systems that extract and reason over medical records and application data. You’ll experiment, iterate, and ship quickly, working alongside a cross-functional team in a dynamic, fast-fail environment. You'll own the evals that prove your system works, and the guardrails that keep it working once real users depend on it. Your work will have a direct impact on our product and business as we push the boundaries of what’s possible with AI.

Задачи

Design, experiment, and deploy production LLM and agentic systems. Quickly test hypotheses, optimise, and iterate based on real-world feedback and eval results. Build and maintain the evaluation harness that tells us whether a model or prompt change made things better or worse. Architect multi-step, tool-using pipelines with explicit state, guardrails, and human-in-the-loop review where the stakes demand it. Push the envelope with cutting-edge LLM and agentic techniques to solve hard problems in language understanding, extraction, and reasoning. Collaborate with Product, Design, and Underwriting SMEs to align ML capabilities with product goals and real domain constraints. Take systems from prototype to production, optimising for latency, cost per run, and reliability at scale.

Требования

6+ years in ML/AI, with deep hands‑on expertise in NLP, LLMs/SLMs, and agentic systems. Hands‑on experience building with OpenAI and Anthropic models/APIs; strong knowledge of LLMs and agent architectures. Practical experience with LiteLLM, vLLM, Langfuse (or equivalent LLM observability tooling). Proven ability to design, build, and own evaluation harnesses for LLM/agent outputs. Proven ability to design and optimise prompts and context, including techniques like few‑shot, chain‑of‑thought, and prompt tuning techniques, grounded in measurable evaluation rather than guesswork. Strong Python skills, with FastAPI for service development, Postgres (or similar) for data persistence, and comfort with event‑driven, async architectures. Working knowledge of ML frameworks (PyTorch, TensorFlow), containerisation with Docker and Kubernetes, and cloud platforms (AWS preferred). You care about whether the system actually solves the underwriter's problem, not just whether the model scores well. You're comfortable challenging the spec, proposing a different approach, and owning your feature from idea through to production impact. Entrepreneurial, ownership‑driven, and biased to action, with a "Build Fast, Fail Fast" approach, thriving in agile, iterative environments. Будет плюсом: Experience with Claude Code/Codex and associated coding‑agent workflows is a plus; Prior experience with DSPy, GEPA, or similar is a plus

Условия

This means working in an environment where you can really make a difference and where the opportunities for continuous learning and development are abound. Unlike many other scale‑up Tech companies, we have the financial backing of our successful parent company. This means we can offer a number of benefits and programmes to reward and recognise our employees’ contributions, which reflect the value we place on our employees. From competitive salaries and bonus schemes to wellness offerings and a hybrid working approach that facilitates a healthy work‑life balance We also take pride in giving back to the community and offer rewarding volunteering and social responsibility opportunities. 25 days of annual leave with option to buy/sell more days Adoption and fertility leave Generous enhanced parental leave Comprehensive private insurance coverage for employee and dependents Group Life Insurance coverage of 9x basic annual salary and Group Income Protection up to 75% of basic annual salary Optical benefits 15% combined employee/employer contributions Subsidized gym membership Access to Employee Assistance Program Cycle to Work and Electric Car Salary Sacrifice Scheme Time off for volunteering Charitable matching of employee donations