11 months ago
London, United KingdomSenior
Responsibilities
- Design, build, and refine production-grade LLM agents and proprietary algorithms for expert litigators
- Lead development of evaluation frameworks and pipelines, including metrics and model benchmarking on large datasets
- Drive advanced prompt-engineering practices to maximize model efficacy
- Apply NLP fundamentals such as tokenisation, embeddings, and model architecture
- Own clean, modular Python backend code for data-intensive systems
- Balance token limits, cost, latency, performance, and structured outputs
- Contribute directly to Wexler’s AI strategy and production roadmap
Requirements
- Expert-level Python with 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
- Solid grounding in NLP fundamentals including tokenisation, embeddings, and bias handling
- Ability to manage token limits, cost, and latency while delivering structured outputs
- Interest in LLMs, AI experimentation, and building in a fast-paced startup environment
- Willingness to work four days per week in person at the London office
Benefits
- Meaningful early-stage equity
- Budget for learning and professional growth
- Bi-annual team retreats
- London office at WeWork 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.