AI Engineer

Patlytics

United States

On-site

USD 150,000 - 210,000

Full time

14 days+

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Job summary

Patlytics is seeking an AI Engineer to architect and deploy scalable AI/ML algorithms for patent intelligence. You will design multi-step LLM pipelines for claim analysis, infringement detection and prior art search, including model selection and prompt architectures.

You will build retrieval systems optimized for long patent documents, coordinate tool use in an Agent layer, and collaborate with attorneys to encode domain judgment into prompts and datasets.

Qualifications

  • Shipped LLM-powered features with production monitoring and fallbacks.
  • Strong Python and backend systems development experience.
  • Experience building ML pipelines end-to-end.
  • Familiarity with prompts, evaluation, and prompt tuning.

Responsibilities

  • Develop and deploy robust, scalable AI/ML algorithms for IP applications
  • Design and iterate multi-step LLM pipelines for patent analysis
  • Build and maintain an evals framework with golden datasets and regression tests
  • Develop retrieval systems (vector search, BM25, re-ranking) for patent corpora
  • Architect and ship agentic workflows coordinating tools, memory, and reasoning
  • Develop data classification techniques and post-training on latest LLMs
  • Collaborate with patent attorneys to encode expert judgment into prompts and datasets
  • Own cost, latency, and quality tradeoffs for production inference: caching, context/window management, batching, model migration

Skills

LLM pipelines
Python
Backend
Prompt engineering
Data pipelines

Tools

AWS
GCP
LLM providers

Job description

About Patlytics

Patlytics is the fastest-growing AI-native patent intelligence platform, transforming how IP is protected and monetized at scale. Our advanced LLMs and generative AI engine-custom-built for intellectual property-power every phase of the patent workflow from invention disclosure through litigation, delivering citation-backed insights with unprecedented accuracy and speed.


Fresh off our $40M Series B - led by SignalFire , with participation from N47 , Myriad Venture Partners , Liquid 2 Ventures , BAM Corner Point , Alumni Ventures , Antiportfolio Ventures and Relativity - allows us to triple down on the product, accelerate growth globally, hire future mission-aligned colleagues, and to continue redefining what is possible for our customers. - we're scaling fast across product, engineering, and go-to-market. If you want to build at the inflection point, this is it.


With teams across the globe we're building a global company fueled by exceptional talent and bold ideas. Our rapid expansion is driven by people who bring entrepreneurial energy, intellectual curiosity, and a shared commitment to setting the global standard for AI-powered IP intelligence. We're creating a culture where diverse perspectives shape breakthrough innovation and every voice contributes to transforming how the world protects ideas.


We hire for trajectory, not just credentials.


As an AI Engineer, you'll:


  • Develop and deploy robust, scalable AI/ML algorithms for cutting-edge IP applications

  • Design, implement, and iterate on multi-step LLM pipelines for patent claim analysis, infringement detection, and prior art search, including the model selection, prompt architecture, and structured output contracts that define product quality

  • Build and maintain a rigorous evals framework: define success metrics per pipeline stage, curate golden datasets from real IP cases, and run continuous regression testing to catch degradation before users do

  • Develop retrieval systems (vector search, BM25 hybrids, re-ranking) optimized for patent corpus characteristics, long documents, technical claim language, biological sequence identifiers

  • Architect and ship agentic workflows within our Agent layer, coordinating tool use, memory, and multi-turn reasoning over complex IP research tasks

  • Develop data classification techniques and post-training on the latest LLMs

  • Collaborate with patent attorneys and domain experts to encode expert judgment into prompts, rubrics, and fine-tuning datasets, then measure whether it worked Own cost, latency, and quality tradeoffs for production inference: prompt caching strategies, context window management, batching, and model migration planning on AWS, GCP and other LLM providers.

  • Partner with a highly talented cross functional group of researchers, applied scientists, engineers, and product managers to build and evolve the (your company's platform, product, solution, etc.)

  • Work with large, complex data sets, solve difficult, non-routine analysis problems, and apply advanced analytical methods as needed

  • Partner with the Leadership Team to align development strategies with key product requirements and long-term technical roadmap

  • Build tools to monitor data pipeline performance, data quality and models in production

  • Perform unit testing, profiling, and parameter tuning

  • Collaborate with data engineers & platform team to implement data pipelines and robust production real-time and batch decisioning solutions

  • Lead ongoing R&D of new technologies, data sources and data science & optimization tools

  • Improve existing machine learning methodologies by developing new sources and testing enhancements, running computational experiments, and fine-tuning parameters


That said, these responsibilities are just the beginning! As we continue to grow, we encourage you to contribute wherever you observe opportunities in the business that align with your interests.


About you:


  • You've shipped LLM-powered features that real users depend on, not just demos or side projects. You have a track record of turning prototype prompts into production pipelines with monitoring and fallbacks

  • You think in evals first. Before writing a prompt, you ask 'how will we know if this is better?' and you build the scaffolding to answer that question rigorously

  • You're comfortable with ambiguity at the model layer. You know that Claude, GPT, and Gemini make different tradeoffs, and you've developed intuition for when to switch, fine-tune, or route between them

  • You write solid Python and have enough backend instincts to own a service end-to-end: API design, data pipelines, async processing, and observability

  • You can read a patent claim and not immediately give up. You're curious about domain knowledge and willing to become a genuine expert in IP reasoning over time

  • You have a strong technical background building ML & AI pipelines

  • You have great understanding of ML methods and statis

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

AI Engineer
AI Engineer

Patlytics • New York (NY)

Hybrid
USD 120,000 - 160,000
Comprehensive health coverage
Unlimited PTO
Immediate 401(k) enrollment
+2
Senior Product Manager
Senior Product Manager

Patlytics • United States

On-site
USD 150,000 - 190,000
Legal Engineer
Legal Engineer

Patlytics, Inc. • New York (NY)

On-site
USD 150,000 - 210,000
Legal Engineer
Legal Engineer

Patlytics • New York (NY)

On-site
USD 150,000 - 210,000
Staff Product Manager
Staff Product Manager

Patlytics • New York (NY)

On-site
USD 140,000 - 220,000
Health coverage
401k enrollment
Unlimited PTO
+3
Senior AI Engineer
Senior AI Engineer

withpulley • San Francisco (CA)

On-site
USD 180,000 - 280,000
AI Engineer
AI Engineer

Valsoft Corporation • United States

Remote
USD 150,000 - 210,000
Full-Stack Engineer
Full-Stack Engineer

IP Author Inc • United States

On-site
USD 120,000 - 180,000
Legal and Product Engineer (Japanese Speaking)
Legal and Product Engineer (Japanese Speaking)

solveintelligence • New York (NY)

Hybrid
USD 140,000 - 210,000
Senior Product Designer
Senior Product Designer

Patlytics, Inc. • New York (NY)

Hybrid
USD 120,000 - 150,000
Comprehensive health coverage
Mental health and wellness support
Immediate 401(k) enrollment
+5