AI Engineer
| Company | Ironclad |
|---|---|
| Location | San Francisco, CA, USA, New York, NY, USA |
| Salary | $145000 – $165000 |
| Type | Full-Time |
| Degrees | Bachelor’s |
| Experience Level | Junior, Mid Level |
Requirements
- BS degree in Computer Science, Engineering, or a related field
- Experience in training, evaluating, and serving machine learning models in production
- 1+ years of hands-on experience with Python, backend service development, and RESTful APIs
- 1+ years of experience in NLP techniques such as text classification, entity extraction, document understanding, or question answering
- Proficiency with deep learning frameworks and APIs (e.g., PyTorch, TensorFlow, HuggingFace Transformers, OpenAI APIs, LangChain)
- Experience with cloud platforms (e.g., GCP, AWS, Azure)
- Solid understanding of Git or other version control systems
- Strong engineering fundamentals and attention to code quality, testing, and maintainability
- Excellent communication and collaboration skills
- Passion for building AI products that solve real-world customer problems
Responsibilities
- Build models and AI capabilities that ingest legal documents, extract key information, and deliver actionable insights to customers
- Implementing backend services that power document understanding, classification, and natural language search
- Explore and apply cutting-edge techniques in NLP, LLM integration, and semantic search to advance Ironclad’s AI/ML vision
- Design and maintain robust pipelines for model training, evaluation, and inference, with a focus on scalability, reliability, and observability
- Develop and scale retrieval-augmented generation (RAG) systems and agent-based orchestration frameworks for complex legal workflows
- Help build foundational AI/ML infrastructure, including tools for experimentation, model versioning, and online/offline performance monitoring
- Partner closely with product managers and designers to shape user-facing AI experiences and deliver value through APIs and intelligent features
- Own and maintain production systems, responding to high-priority issues (P0s) and resolving bugs as they arise
Preferred Qualifications
- Experience working with large language models (e.g., GPT, Claude) or building RAG systems
- Experience with embedding models and vector databases
- Familiarity with Vertex AI or other managed ML platforms
- Experience working with PDF and DOCX parsing for document ingestion
- Comfort with Docker and containerized development
- Familiarity with CI/CD systems (e.g., GitHub Actions, CircleCI)
- Monitoring and observability with tools like Datadog or equivalent
- Experience with data processing and analysis using tools like SQL, Pandas, NumPy, or PySpark