Software Development Engineer - II | Backend (AI POD)

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.

Job Summary

SpotDraft is revolutionizing legal operations with AI-powered tools that help legal teams work faster and smarter. Our flagship products leverage cutting-edge LLM technology to automate routine legal work and accelerate contract review.
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 SpotDraft. It tackles everything beyond contracts, including policy questions, regulatory compliance, and strategic advice SpotDraft, learning from your organization’s knowledge to become a specialized legal co-pilot.
VerifAI is an AI contract review tool that works as a Microsoft Word add-in, helping legal teams review contracts up to 70% faster with SpotDraft. It uses generative AI to check contracts against personal or organizational guidelines and answer open-ended questions SpotDraft, automatically flagging deviations and suggesting improvements.

About the role

We’re looking for a Backend Engineer to join the AAI Pod — the team building SpotDraft’s AI-powered product capabilities, including data/text extraction, contract intelligence, and LLM-driven features layered on our core contracting platform. You’ll help architect, build, and scale backend systems that power these AI features end-to-end, working closely with Product, Engineering, and AI teams to ship high-impact capabilities that our customers directly experience.

This role sits at the intersection of strong backend fundamentals and applied AI — you won’t just be calling an API, you’ll be designing the systems (extraction pipelines, RAG architectures, orchestration layers) that make AI features reliable and scalable in production.

What you’ll do

System Design & Architecture

• Design and build scalable backend systems for AI-powered features, with a strong focus on reliability and performance
• Own end-to-end system design (HLDs & LLDs) for extraction pipelines and AI feature integration
• Make thoughtful trade-offs balancing speed, scalability, and maintainability in systems that call LLMs or process high volumes of documents/text

AI & Extraction Systems

• Build and operate data/text extraction pipelines that power downstream AI features
• Design and implement RAG pipelines, LLM integrations, or agentic workflows as part of product features
• Own the reliability and cost-efficiency of AI-integrated systems — caching, fallback handling, and failure recovery for LLM-dependent services

Product & Engineering Collaboration

• Work closely with Product, Design, and AI teams to ship impactful features
• Translate ambiguous product requirements into clear technical solutions
• Participate in cross-functional discussions and influence product direction

Execution & Ownership

• Own features and systems end-to-end — from ideation to production and beyond
• Build systems from scratch and evolve them as they scale
• Take accountability for reliability, performance, and uptime of owned systems

Team & Culture Contribution

• Contribute to hiring by participating in interviews and candidate evaluation
• Mentor junior engineers and raise the overall engineering bar
• Bring a strong “builder’s mindset” with a bias for action and problem-solving

What We’re Looking For

Must haves

• 4–7 years of experience in backend/software engineering (minimum 4–5 years)
• Strong backend engineering fundamentals — proven experience architecting and building scalable products/features end-to-end (not just feature-level execution)
• Hands-on experience with system design (HLD & LLD)
• AI/ML exposure — either has built/implemented a RAG pipeline, or has integrated/used LLMs in a production application
• Experience with data or text extraction pipelines — this is core to the pod’s work, not a peripheral skill

Should haves

• Distributed systems experience — queues, async processing, caching
• Familiarity with vector databases / embeddings (Pinecone, Weaviate, pgvector, etc.)…