Software Engineer, Staff (Applied AI) at Lightfield in HQ: San Francisco

Job description

• Application
• We’re looking for a driven, creative engineer who is excited about the challenge of leveraging LLMs to build exceptionally innovative product experiences.
• You’ll join us at the frontier of AI product development, developing industry-leading approaches to solve important customer problems.
• Engineers at Lightfield own and drive projects from inception to impact, working with teammates of all functions along the way.
• You’ll also push our company’s overall product and technical vision as we learn from each project and continue to scale.

Responsibilities

• Collaborate with product leaders to identify customer problems, scope requirements, and implement LLM-powered solutions.
• Apply LLMs as reasoning engines to build domain-specific AI assistants.
• Create and enhance prompts, applying techniques like few-shot learning and chain-of-thought.
• Develop and optimize end-to-end RAG pipelines and agent architectures to leverage public and proprietary data.
• Improve end-to-end AI agent quality (e.g. relevance, fidelity, latency) via empirical evaluation and iteration.
• Build and enhance systems and tools that enable high-velocity experimentation (e.g. LLM-powered automated evaluation) and customized product experiences.
• Stay at the forefront of AI research and incorporate state-of-the-art techniques.
• Shape technical direction and best practices for AI application development at Lightfield.
• Help build a world-class engineering team by recruiting and mentoring teammates.

Requirements

• You have 7+ years experience and the ability to ramp up quickly on a tech stack that features TypeScript, React, Next.js, Node.js, Apollo GraphQL, and Aurora PostgreSQL.
• You have explored working with LLMs, either through professional projects or personal experimentation.
• You have a degree in Computer Science or a related field, with a strong foundation in software engineering principles.
• You are familiar with AI and ML concepts (e.g. training, evaluation techniques).
• You are passionate about keeping up with and exploring the latest advancements in LLMs and LLMOps (including open source solutions).
• You are excited to develop new best practices in an emerging domain.
• You can drive a project with an ambiguous problem independently.
• You enjoy strategically balancing ambitious vision with frequent delivery of user value.
• You are able to clearly communicate your reasoning and decisions to your teammates (technical and nontechnical) at an appropriate altitude of detail.
• You are energized by building software experiences customers will use directly and depend on to do their jobs successfully.

Skills

Required

• TypeScript
• React
• Next.js
• Node.js
• Apollo GraphQL
• Aurora PostgreSQL
• LLMs
• AI/ML concepts
• LLMOps
• RAG pipelines
• Agent architectures
• Empirical evaluation

Benefits

• Competitive salary
• Meaningful early equity
• Health insurance (medical, dental, vision)
• 3 weeks of PTO
• 11 paid company holidays + we enjoy a winter holiday break
• 3 months of paid family leave
• Wednesdays work from home
• Regular team dinners, events, offsites, and retreats
• 401k plan
• Other perks include: commuter and lunch stipend