1 year ago
London, United KingdomSenior
Responsibilities
- Design, build, and refine production-grade LLM agents and proprietary algorithms for expert litigators.
- Lead evaluation frameworks and end-to-end pipelines, including metrics and model benchmarking on large datasets.
- Develop advanced prompt-engineering practices to improve model efficacy.
- Apply NLP fundamentals including tokenization, embeddings, model architecture, and bias handling.
- Own clean, modular Python backend code for data-intensive systems while balancing token limits, cost, latency, and structured outputs.
- Shape AI strategy and turn new ideas into production systems for enterprise legal clients.
Requirements
- Expert-level Python experience and a track record of shipping production LLM systems.
- Hands-on experience designing LLM agents and RAG pipelines.
- Proficiency with AI evaluation frameworks and end-to-end evaluation pipelines.
- Strong grounding in NLP fundamentals, including tokenization, embeddings, and bias handling.
- Ability to optimize structured outputs under token, cost, and latency constraints.
- Interest in AI and LLMs and readiness to work in a fast-paced startup environment with evolving priorities.
Benefits
- Competitive salary and meaningful early-stage equity.
- High autonomy and ownership over AI systems used by leading law firms and enterprise clients.
- Budget for learning and professional growth.
- Bi-annual team retreats.
- London office-based work at WeWork in Aldwych, with four days per week in person.
Tech Stack
Categories
About Pear VC
Pear VC is an early-stage venture capital partnership that invests at pre-seed and seed, pairing capital with hands-on support, mentorship, and programs like its PearX accelerator for founding teams. Founded in 2013 and headquartered in Menlo Park, California, it backs software and technology startups across categories. Its portfolio includes companies that reached the public markets, such as DoorDash and Guardant Health.