5-7 years of experience as an AI Engineer with a focus on ML & AI pipelines
Proven track record of deploying LLM-powered production features
Strong technical background with a solid understanding of ML methods and statistics
Experience with cloud service maintenance and deployment (AWS, GCP)
Proficiency in Python and backend system design
Ability to navigate complex patent claims and a willingness to build domain knowledge
Familiarity with data transformation tools like Pandas and Spark and SQL
Responsibilities
Develop and deploy scalable AI/ML algorithms for innovative IP applications
Design and iterate multi-step LLM pipelines for patent-related analyses
Build an evaluation framework with metrics to ensure quality in production
Create and maintain retrieval systems tailored for patent document characteristics
Architect workflows for complex IP research tasks using agent-based systems
Collaborate with experts to optimize prompt engineering and datasets
Lead ongoing R&D for new data science technologies and methodologies
Benefits
Comprehensive health coverage including medical, dental, and vision
Mental health support and wellness programs
Immediate enrollment in a 401(k) plan
Generous unlimited PTO and paid company holidays
Family-first policies including paid parental leave
Professional development budget and gym membership stipend
Recognition programs for birthdays and anniversaries
Flexible hybrid work environment
Full Job Description
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 statistics, including ML project lifecycle and associated challenges at each stage of development
Experience deploying, monitoring and maintaining data science products in cloud environments such as AWS and GCP.
Solid understanding of data transformations and analytics functions using tools/languages like (Pandas, Sklearn, SQL, Spark, etc.)
Familiarity with database modeling, data warehousing principles and SQL
If you don't meet 100% of the above qualifications, you should still consider applying. Studies show that you can still be considered for a role if you meet just 50% of the position's requirements.
We offer:
Comprehensive health coverage - Medical, dental, vision, plus FSA, commuter benefits, and health advocacy through Rightway
Mental health & wellness support - Access to Spring Health and Headspace, plus "Mental Escape Days" to recharge when you need it
Immediate 401(k) enrollment - No waiting period to start saving for your future
Generous time off - Unlimited PTO, 12 paid company holidays, plus a full week off during our Holiday Break
Family-first policies - Paid parental leave to support you during life's biggest moments
Invest in yourself - Professional development budget, gym membership stipend, and learning opportunities
Celebrate what matters - Birthday and work anniversary recognition, plus generous employee referral bonuses
Hybrid work environment (open to remote pending location), while staying connected with a passionate and talented team
