Senior AI/LLM Engineer
Build and scale AI-powered features for internet-scale security intelligence, including LLM and RAG systems, analytics, and workflow automation. The role requires 5+ years of software engineering experience, strong Python skills, and experience delivering secure, user-facing AI applications.
About the job
Responsibilities
- Rapidly prototype and deploy AI-powered features to enhance search, improve recommendations, and automate workflows across the Censys Platform.
- Apply machine learning to streamline workflows, personalize experiences, and surface critical insights.
- Develop and fine-tune LLMs and retrieval-augmented generation (RAG) pipelines to reason over Internet-scale data, summarize findings, and deliver context-aware insights.
- Build, scale, and maintain AI-driven analytics and automation systems that help users make faster, data-backed decisions.
- Collaborate with frontend, product, and data engineering teams to integrate secure, seamless AI-native experiences.
- Continuously evaluate and improve model performance through RAGAS, LangSmith, and automated regression testing frameworks.
Requirements
- 5+ years of software engineering experience, including 2+ years building and scaling AI-powered user-facing features.
- Strong proficiency in Python for backend and API services development.
- Familiarity with RAG evaluation frameworks such as RAGAS and LangSmith, and with designing regression testing for LLM pipelines.
- Ability to rapidly prototype, validate, and refine AI features in an experiment-driven environment.
- Knowledge of prompt engineering to improve LLM accuracy, reasoning, and consistency.
- Understanding of secure and responsible AI practices, including guardrails and safety checks to prevent misuse or data exposure.
- Hands-on experience with CI/CD pipelines, test automation, and deployment best practices for AI applications.
- Strong cross-team collaboration skills.
Nice-to-haves
- Advanced knowledge of AI/ML architectures, model evaluation, and applied deep learning.
- Experience with RAG, vector search, and LLM fine-tuning.
- Understanding of embedding models and AI-driven analytics.
- Ability to optimize AI models for low-latency, real-time interactions in browser or frontend environments.
- Experience deploying secure AI systems in cybersecurity or other sensitive-data domains.
- Experience leveraging AI tools to improve coding productivity and product capabilities.
Compensation and Benefits
- For high-cost-of-living areas including San Francisco Bay, New York City, and Seattle: $179,000–$201,000 USD, plus bonus eligibility and equity.
- For all other locations: $148,000–$192,000 USD, plus bonus eligibility and equity.
- Benefits include 401(k) match, health, vision, and dental coverage, effective on day one.
Skills
Python, LLMs, Retrieval-Augmented Generation, Ragas, Langsmith, Prompt Engineering, Vector Search, Llm Fine-Tuning, Embedding Models, Deep Learning, CI/CD, Test Automation, Machine Learning, Ai Guardrails, Regression Testing
Similar jobs
ML Engineering jobs
Blee
San Francisco, CA
Designs and ships production multi-agent compliance systems, including LLM pipelines, model training, evaluation, monitoring, and explainability. Requires 5+ years of applied AI/ML engineering experience, strong Python, and experience deploying production ML systems.
Censys
United StatesBuild and deploy production machine-learning models and data systems that classify and enrich Internet telemetry for internal platforms and customer-facing products. The role requires 5+ years of applied ML, data science, or software engineering experience, plus strong Python or Go skills.
Apartment List
United StatesBuild marketplace search and ranking features while supporting MLOps infrastructure, model deployment, feature stores, and real-time data pipelines. The role requires 5+ years of software engineering or MLOps experience, backend or full-stack expertise, and familiarity with cloud and machine learning tooling.
Mercury
San Francisco, CABuild and operate the platform that deploys, serves, observes, and retrains production machine-learning models for real-time fraud and financial-crime risk decisions. Requires 5+ years of ML engineering, backend, or MLOps experience, strong Python skills, and production model-serving expertise.
LangChain
New York, NY
Leads hands-on development and deployment of production AI agents and workflows, sets technical standards, and mentors engineers. Requires 4+ years of software engineering experience, production LLM application experience, and strong Python or TypeScript skills.