Foundation AI is the only AI Native document intake automation platform serving the claims and litigation industries. Founded in 2019 by a team of lawyers and data scientists, Foundation AI processes millions of documents each month for hundreds of US law firms, including many of the largest and most respected plaintiff and injury law firms in the country.
Job OverviewWe're looking for a Senior AI/ML Engineer to help expand our next-generation document intelligence system. Working in close collaboration with our Data Science team, you'll bring deep technical rigor to a system that gets smarter with every document it digests, across hundreds of customers at scale. The system draws on a combination of ML, LLM, RAG, applied mathematics, and smart algorithm design to deliver results at a high level of accuracy.
this is a remote job.
- Retrieval-Augmented Generation: Design and build RAG architectures for document understanding, classification, and extraction — from chunking and indexing through retrieval quality and grounding.
- LLM Feature Development: Ship production LLM-powered features end-to-end, from prompt design through evaluation — not just prototypes.
- Evaluation-Driven Development: Build regression suites, confidence calibration methods, and evaluation frameworks that make AI output quality measurable.
- Collaboration with Data Science: Partner closely with our Data Science team to bring research-grade techniques into production.
- ML Pipeline & MLOps: Own model, data, and prompt versioning; build reproducible pipelines for ingestion, training, evaluation, and serving.
- Rollout Automation & A/B Testing: Implement canary deployments, side-by-side A/B testing, and rollback mechanisms for safe model and prompt releases.
- Monitoring & Observability: Implement drift detection, data quality monitoring, and alerting; define SLOs for model and pipeline health.
- System Architecture & Leadership: Design secure, high-performance ML infrastructure; evaluate tooling (Bedrock, MLflow, Airflow); mentor engineers and influence best practices.
- Experience: 5+ years in software engineering, with 2–3 years focused on ML/AI in production systems.
- LLM & RAG Fundamentals: Hands-on experience with prompt engineering, RAG architectures, and evaluation-driven development — with a track record of shipping LLM-powered features real users rely on.
- MLOps & Pipeline Tooling: Practical experience with model/data/prompt versioning, experiment tracking, and deployment automation; proficiency with Airflow, MLflow, and Bedrock or equivalents.
- Programming: Proficient in Python; comfortable with SQL and data engineering patterns.
- Strongly Preferred: Working understanding of classical ML methods (gradient boosting, embeddings, calibration) sufficient to collaborate closely with Data Science; AWS infrastructure experience (S3, ECS/EKS, Lambda); familiarity with agent frameworks (LangChain, MCP) is a bonus.
A B.Tech degree in Computer Science or equivalent experience relevant to the functional area.
Our CommitmentFoundation AI is an equal opportunity employer committed to diversity and inclusion in the workplace. We prohibit discrimination and harassment of any kind based on race, color, sex, religion, sexual orientation, national origin, disability, genetic information, pregnancy, or any other protected characteristic. Our hiring decisions are based solely on qualifications, merit, and business needs at the time.
For any feedback or inquiries, please contact us at [email protected]. Learn more at www.foundationai.com.
Skills Required
- 5+ years in software engineering with at least 2-3 years in ML engineering, MLOps, or AI platform roles.
- Hands-on experience with model versioning, data versioning, prompt versioning, experiment tracking, and deployment automation in production.
- Proficiency with workflow orchestration (Apache Airflow or equivalent).
- Experience with experiment tracking tools (MLflow or equivalent).
- Experience with cloud-based model hosting (AWS Bedrock or equivalent).
- Experience designing and operating side-by-side deployments, shadow mode evaluation, canary releases, and automated rollback strategies.
- Familiarity with model drift detection, data quality monitoring, and defining/tracking ML-specific SLOs.
- Experience with AWS services: S3, ECS/EKS, Lambda, Step Functions (or equivalents).
- Proficient in Python and writing scalable, maintainable, secure code.
- Experience with CI/CD for ML including automated training pipelines, evaluation gates, and model promotion flows.
- Experience mentoring engineers and providing technical leadership.
- B-Tech degree in Computer Science or equivalent experience.
- Familiarity with SQL and data engineering patterns.
What We Do
Foundation AI helps law firms and claims departments streamline the manual and error-prone process of managing inbound mail and emailed documents. The platform profiles inbound documents to the right claim or matter, classifies each by type, and extracts critical information to streamline downstream workflows. It names and saves each document to the right folder in your document management system, alerts the responsible party, and even automates data entry into your downstream systems. Automate your document intake. Your people have better things to do.
.png)
