Komodo Health is seeking a Senior Software Engineer to design, build, and scale the company's AI-powered Public Data Acquisition, Extraction, and Curation Platform. This role is crucial for transforming how unstructured and semi-structured data is handled to generate structured insights, directly powering Komodo's Data and Products, and evolving the platform to handle new domains and increasing complexity.
Requirements
- Strong Python, No SQL, SQL, Vector DBs, AWS (such as Lambda, Step Functions and Fargate) skills.
- Experience with infrastructure-as-code (Such as CloudFormation, CDK, Terraform)
- Experience with Large Language Models (LLMs), RAG, and AI-driven data handling or related areas such as information retrieval or process automation
- Experience in scaling APIs, preferably for data processing.
- Experience with orchestration tools, version control (Git), CI/CD (Github Actions)).
- Experience planning, breaking down, and estimating engineering tasks using standard software development methodologies.
- Ability to leverage AI tools (Gemini, ChatGPT, Cursor, etc.) to enhance personal productivity, streamline workflows, or improve decision-making
Responsibilities
- Design, build, and scale Komodo Health’s AI-powered Public Data Acquisition, Extraction, and Curation Platform.
- Drive innovation at the intersection of Automation and Generative and Agentic AI to scale acquiring and handling of public data and optimizing human-in-the-loop workflows.
- Evolve the platform to handle the complexity, variability, and scale to include new domains.
- Design, develop, and maintain scalable and intelligent data crawling & scraping infrastructure and tooling.
- Develop scalable and generalizable data extraction processes and APIs, leveraging Generative and Agentic AI for entity and relationship extraction.
- Develop AI-driven intelligence, automation, and tooling for linking, validation, and enhancement of extracted data, incorporating human-in-the-loop processes, with automated change detection and curation workflows.
- Develop APIs and platform capabilities to provide visibility, operational insights, and optimization across all stages of data acquisition, extraction, and curation workflows and processes.
Other
- 8+ years of hands-on software engineering experience, with expertise in designing scalable, distributed systems.
- Strong communication and leadership skills, with the ability to translate complex technical challenges into actionable solutions.
- Experience with AI agentic workflows.
- Hybrid work model; roles may be completely remote based anywhere in the country listed, remote but based in a specific region, or local (commuting distance) to one of our hubs in San Francisco, New York City, or Chicago with remote work options.
- Equal employment opportunities to all applicants and employees. We prohibit discrimination and harassment of any type with regard to race, color, religion, age, sex, national origin, disability status, genetics, protected veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by federal, state, or local laws.
