Skip to content
IroncladIroncladSan Francisco, CA

Staff Software Engineer - Applied AI

Develops full-stack AI features for legal contracting platform using TypeScript, React, Node.js, and LLMs. Builds scalable SaaS products like summarization and redlining, collaborating with product and design teams to deliver high-impact capabilities.

240k – 295k
HybridML Engineering

About the role

What you'll be doing

  • Full Stack Development: Lead the design, development, and deployment of features from end-to-end using TypeScript, Node.js, React, and PostgreSQL, ensuring high performance and availability.
  • Build Production AI Features: Be a primary contributor to the next generation of AI-powered legal features, including specialized summarization, drafting, editing, and document comparison functionalities utilizing LLMs.
  • Architect Highly Scalable AI Products: Build and maintain reliable, highly scalable software and services designed for a high-traffic SaaS environment.
  • Foster Cross-Functional Collaboration: Collaborate closely with Product Managers, UX Designers, and QE counterparts to rapidly prototype, iterate on designs, and make frequent, agile pivots based on user feedback.
  • Advocate for the Customer: Maintain a high degree of customer empathy, ensuring technical decisions prioritize user experience and directly address customer pain points, creating measurable product impact.
  • Deliver and Optimize AI Infrastructure: Work with platform teams to consume and manage internal LLM APIs, ensuring resilient connections and efficient token usage to meet strict latency targets.

Required Skills

  • Full-Stack Expertise: Deep professional experience with the core tech stack: TypeScript, Node.js, React, and PostgreSQL.
  • High-Scale SaaS Experience: Proven track record of building, deploying, and maintaining reliable, highly scalable software for SaaS applications.
  • LLM Consumption and Integration: Extensive experience consuming LLMs via APIs (e.g., OpenAI, Gemini, or proprietary models) and integrating them successfully into production-facing features.
  • AI Feature Implementation: Practical experience building and shipping accurate and successful AI features or products, such as chatbots, summarization, drafting, or document editing/comparison using LLMs, RAGs, and the right context for LLM calls.
  • Analytics, Monitoring and Observability: Experience with making data driven decisions, based on product analytics and have experience using monitoring and observability tools like Datadog or equivalent to diagnose performance issues and ensure system health.
  • Agile and Impact-Driven: Highly agile mindset with proven ability to work effectively in 0-to-1 setups, frequently make pivots, and translate ambiguity into concrete, impactful engineering work.
  • Collaboration and Communication: Exceptional skills as a great collaborator with product, design, and QE teams, acting as a clear technical voice for customer-centric solutions.

Nice to Have Skills

  • AI Evaluation Experience: Experience building automated evaluation pipelines and defining technical metrics (e.g., faithfulness, groundedness) to measure the quality of various AI features.
  • Cloud Administration (GCP/Azure/AWS): Hands-on experience with managing infrastructure or administrative tasks on major cloud providers like GCP, Azure, or AWS.
  • Legal Tech Domain: Prior experience in Legal Tech or other high-stakes domains (FinTech, HealthTech) where data accuracy and auditability are paramount.
  • Document Processing: Experience working with PDF and DOCX parsing for document ingestion.
  • Familiarity with CI/CD systems (e.g., GitHub Actions, CircleCI).

Compensation

Base Salary Ranges:

  • Staff: $210,000 - $260,000
  • Senior Staff: $240,000 - $295,000

The base salary range represents the minimum and maximum of the salary range for this position based at our San Francisco headquarters. The actual base salary offered for this position will depend on numerous factors, including individual proficiency, anticipated performance, and the location of the selected candidate.

Skills

TypeScriptNode.jsReactPostgresLLMsRAGOpenAIGeminiDatadogSaaSGCPAWSAzureCI/CDGitHub Actions

Similar roles

ML Engineering jobs
Traba

Staff Software Engineer

TrabaNew York, NY +1

Build and scale Traba's applied AI platform for industrial supply chain staffing and operations. Architect core backend systems integrating frontier models and agents for automation, matching, and vetting while owning performance and infrastructure.

240k – 300k
Hybrid7+ YOEML Engineering
Traba

Staff Software Engineer

TrabaNew York, NY +1

Build and lead Traba's agentic AI platform as a founding member of the Agents team. Architect orchestration, evals, model strategy, and integrations for autonomous agents in industrial supply chain workflows. Requires 7+ years engineering experience including production LLM/agent systems, with customer immersion and 0-to-1 build experience.

240k – 300k
Hybrid7+ YOEML Engineering
Linktree

Staff Applied AI Engineer, AI Experiences & Agents

LinktreeLos Angeles, CA +1

Build and ship production-grade AI agents and experiences that help creators personalize, automate, and grow. Requires strong product engineering skills, hands-on LLM/agent experience, and rigorous evaluation practices.

240k – 250k
On-siteML Engineering
Fieldguide

Staff AI Engineer

FieldguideSan Francisco, CA

Staff AI Engineer shapes technical direction of AI agents for audit workflows, owning architecture, LLM infrastructure, and reliability systems. Requires 8+ years experience with deep expertise in TypeScript/Python, RAG, and enterprise-scale LLM products.

240k – 310k
Hybrid8+ YOEML Engineering
Runway

Member of Technical Staff, Inference

RunwayUnited States

ML infrastructure engineer productionizing generative AI models from research to scale, optimizing multi-GPU inference, and building reliable serving systems. Requires 4+ years ML inference experience, PyTorch, Kubernetes expertise.

240k – 290k
Remote4+ YOEML Engineering