AI Engineering Intern
About SpotDraft
SpotDraft is on a mission to help legal and business teams move faster, together. Our AI-powered contracting platform is redefining how companies manage contracts, and our story deserves to be told in creative, human, and memorable ways.
About the Role
We're looking for curious, technically strong interns to join the AAI Pod — the team building SpotDraft's AI-powered products, including Sidebar and VerifAI.
Sidebar is an AI-powered team of legal assistants that handles routine legal work — from contract analysis and legal research to compliance tracking and drafting. VerifAI is an AI contract review tool that helps legal teams review contracts up to 70% faster, automatically flagging deviations and suggesting improvements.
As an AI Intern, you'll work alongside experienced engineers to contribute to real production AI systems — not toy problems. You'll ship code that processes legal documents, supports retrieval pipelines, and helps measure the quality of LLM outputs. This is a hands-on role with a steep learning curve and direct exposure to how AI is built at scale in a fast-moving startup.
What You'll Do
Build AI Features
Implement and iterate on prompts for legal document workflows (summarization, clause extraction, drafting assistance)
Integrate LLM APIs (OpenAI, Anthropic, Gemini) into product features under the guidance of senior engineers
Help maintain and version prompt libraries; test prompt variations and document results
Contribute to agentic workflows — tool calling, multi-step reasoning flows — as you build familiarity with the codebase
Support RAG & Context Systems
Assist in building and testing retrieval pipelines: chunking strategies, hybrid search (BM25 + dense embeddings), and reranking for legal documents
Work with vector databases (Pinecone, Weaviate, or pgvector) to support semantic search features
Help tune context window usage and experiment with retrieval configurations
Contribute to Quality & Evaluation
Write evaluation scripts and test cases to measure model output quality (accuracy, hallucination rate, relevance)
Assist with LLM-as-judge pipelines and human-in-the-loop labeling workflows
Participate in A/B testing of prompts, models, and retrieval configurations; help track regressions over time
Infrastructure & Observability
Help maintain monitoring dashboards for latency, token usage, error rates, and cost per request
Write clean, tested Python code within existing service architectures
Assist in debugging issues using logs and traces
What We're Looking For
Must Have
Currently pursuing or recently completed a / / MS in Computer Science, AI/ML, or a related field
Strong Python skills — you can write clean, readable code and pick up new libraries quickly
Basic familiarity with LLM APIs (OpenAI, Anthropic, Gemini, or Llama) — you've called one of these and understand prompt/response structure
Foundational understanding of how LLMs work: transformers, attention, embeddings, tokenization
Some awareness of context engineering — understanding what gets passed into a model's context and why it matters
Comfortable working in a fast-paced environment, asking questions, and iterating based on feedback
Good to Have
A personal project, hackathon, or open-source contribution involving LLMs, RAG, or NLP
Exposure to agentic frameworks (LangChain, LangGraph, LlamaIndex, CrewAI, or similar)
Familiarity with vector databases and semantic search concepts
Coursework or self-study in ML, NLP, or information retrieval
Any experience with evaluation frameworks, synthetic test data, or model output scoring
Interest in legal tech, document intelligence, or OCR/text extraction
What You'll Learn
How production AI systems are designed, built, and maintained at a fast-growing startup
RAG architectures and the nuances of retrieval at scale (chunking, reranking, hybrid search)
LLM evaluation: how to measure hallucination, relevance, and quality systematically
Prompt engineering and context management techniques used in real legal-tech workflows
Working practices of a high-velocity engineering team: code reviews, CI/CD, observability
Why SpotDraft?
Brilliant teammates—Work with some of the sharpest minds in legal tech.
Expand your network—Interact with top founders, investors, and industry leaders.
Real impact—Take ownership of projects and see your work in action.
Big goals, bold moves—We trust you to deliver, innovate, and push boundaries.
Our Core Values
Our business is to delight Customers
Be Transparent. Be Direct
Be Audacious
Outcomes over everything else
Elevate each other
Be Passionate. Take Ownership.
Be 1% better every day
All candidates’ personal data shared during the recruitment process will be handled with utmost confidentiality and used solely for hiring purposes, in line with applicable data protection regulations.
*SpotDraft is an equal-opportunity employer. Candidates will not be discriminated against based on race, ethnicity, color, religion, caste, sex, gender identity, sexual orientation, national origin, veteran, or disability status