Senior Software Engineer, AI Platform
Builds and operates AI platform capabilities including RAG pipelines, semantic retrieval, agentic orchestration, and LLM integrations to power legal tech products. Requires 4+ years in distributed cloud systems, AI/ML experience, and proficiency in modern programming languages.
About the job
Responsibilities
- Build AI platform capabilities powering product experiences like Deep Dive, predictive coding, multi-modal understanding, agentic workflows, translations, search, and review.
- Contribute to RAG, semantic retrieval, and agentic orchestration patterns, including indexing pipelines, query flows, tool-calling, planning logic, relevance tuning, benchmarking, and multi-modal workloads.
- Collaborate with Product, Platform, Security, and DevOps to build and ship features in production.
- Scale system to handle hundreds of millions of documents.
- Provide technical mentorship to engineers and become expert in codebase.
- Perform code reviews using knowledge of languages, design patterns, and best practices.
- Fix defects by triaging issues and writing code to debug, track, and resolve.
- Provide on-call support, answering customer questions, triaging defects, and carrying pager.
- Contribute to internal and external documentation.
- Conduct technical interviews for recruiting.
Requirements
- BS or MS in Computer Science or equivalent.
- Proficiency in coding with C, C++, C#, Java, Python, JavaScript, Go, or Rust.
- Knowledge of algorithms, fundamental CS concepts, relational databases, API design, and building user interfaces.
- Practical experience with AI/ML systems: retrieval pipelines, semantic search, agentic pipelines, document classification, or LLM-integrated features.
- Experience with AI tools like Cursor and Claude Code.
- At least 4 years building distributed cloud systems with service-based architecture, frontend frameworks for rich web apps, and best practices for testing, maintaining, launching cloud software.
- At least 1 year leading or coordinating multi-developer efforts.
Nice-to-haves
- Familiarity with AWS.
- Familiarity with MySQL, Postgres.
- Familiarity with vector or graph databases.
- Familiarity with LLMOps.
Compensation
Salary range: $173,000 - $251,000 (dependent on experience and skills).
Equity program, 401(k) matching, health/dental/vision, FSA, paid parental leave, sick leave, vacation, holidays, mental health benefits, L&D stipend, life/disability insurance.
Skills
Python, JavaScript, Java, Go, Rust, RAG, LLMs, Semantic Search, Vector Databases, AWS, Postgres, MySQL, Distributed Systems, Cloud Architecture, Frontend Frameworks
Similar jobs
ML Engineering jobs
Instacart
United StatesBuild and deploy machine learning systems that apply economic theory, econometrics, and causal inference to marketplace problems. The role requires advanced training in economics, strong Python and data skills, and production ML experience for senior-level hires.
Ai2
Seattle, WA
Senior Research Engineer tailoring and deploying machine learning models for partner applications across geospatial and environmental domains. The role requires PyTorch expertise, end-to-end ML deployment experience, geospatial tools knowledge, and strong independent execution.
Swayable
New York, NYSenior engineer developing and productizing AI, machine learning, scientific computing, and data-analysis capabilities for a high-performance analytics engine. Requires 5+ years building quantitative data-intensive software and expertise in Python, machine learning, scalable architecture, and distributed computing.
Mem0
San Francisco, CA
Own the end-to-end lifecycle of memory features for AI agents. Fine-tune models, implement research, build evaluations, and ship production systems with Engineering.
PrizePicks
United States
Build and ship production Applied AI capabilities, including agent infrastructure, RAG services, evaluation systems, and AI-powered engineering workflows. The role requires 6+ years of software engineering experience, strong backend and distributed-systems skills, and direct experience delivering LLM- or ML-powered products.