Full-Time
AI Engineer
CoreStory
11-50 employees
AI-powered platform for legacy code modernization
No salary listed
Remote in USA
Remote
Remote-first within the United States.
 AI & Machine Learning (1) |
|---|
Get referred to CoreStory
See people who can refer or advise you
- 7+ years of overall engineering experience with at least 3+ years of experience in AI engineering, machine learning, or applied natural language processing
- Strong hands-on experience with LlamaIndex, LangChain, or similar orchestration frameworks
- Experience designing and implementing vector database solutions (e.g., Pinecone, Neo4j, FAISS, Milvus, Weaviate)
- Solid understanding of LLM APIs (OpenAI, Anthropic, Mistral, Hugging Face, etc.)
- Proficiency in Python, with experience in libraries such as FastAPI, Pandas, or NumPy
- Understanding of retrieval-augmented generation (RAG) patterns, embeddings, and tokenization
- Familiarity with prompt engineering, tool calling, and chat agent architectures
- Strong problem-solving and analytical mindset, with attention to performance and scalability
- Demonstrated interest in staying up-to-date with the fast-evolving AI landscape
- Design, implement, and optimize LLM-powered systems (e.g., RAG, chat agents, summarizers, knowledge graph integration)
- Build and manage data indexing and retrieval pipelines using LlamaIndex, LangChain, or similar frameworks
- Implement and maintain vector databases (e.g., Pinecone, Neo4j, Weaviate, Chroma, or Azure Cognitive Search)
- Integrate open-source and proprietary LLMs (e.g., GPT, Claude, Llama) into the CoreStory Platform
- Develop and refine AI-driven features — including generative insights, automated summarization, and narrative analytics
- Collaborate with DevOps and backend teams to deploy scalable AI services within CoreStory’s cloud infrastructure
- Continuously benchmark model performance, latency, and cost, identifying opportunities for optimization
- Stay current with advancements in AI — from model architectures to emerging frameworks — and propose innovative applications aligned with CoreStory’s mission
- Contribute to internal documentation, experimentation frameworks, and evaluation methodologies
- Experience deploying AI services in production (e.g., using Docker, Azure, or AWS)
- Exposure to LangGraph, semantic search, or hybrid RAG systems
- Familiarity with knowledge graphs, document intelligence, or multimodal AI
- Previous experience in SaaS or early-stage startup environments
CoreStory delivers an AI-powered code intelligence platform that helps large enterprises modernize aging legacy software. It reverse engineers complex codebases to produce an Intelligence Model that captures business requirements, system relationships, and developer intent, creating a single source of truth when documentation is missing. The platform can process up to 100,000 lines of code in minutes and translate them into business requirements, user stories, and architectural documentation. It integrates with AI coding assistants to improve work on legacy apps. CoreStory targets Fortune 500 companies and other large organizations to accelerate modernization, reduce risk, and lower the cost and time of projects that historically take 18 months or more. Key use cases include legacy modernization, application maintenance and extension, managing technical debt from AI-generated code, and speeding developer onboarding.
Company Size
11-50
Company Stage
Series A
Total Funding
$32M
Headquarters
Berkeley, California
Founded
N/A
Get referred to CoreStory
See people who can refer or advise you
Simplify's Take
What believers are saying
- July 21, 2026 Evermuse partnership expands distribution through shared MCP partner directories.
- The Greenhouse board showed one open engineering role on July 10, 2026, signaling hiring.
- CoreStory's June 2026 demos claim 2x ticket throughput and 50% human-time reduction.
What critics are saying
- Anthropic's Claude Code already targets modernization, pressuring CoreStory's premium enterprise story by 2026.
- G2 lists CAST Highlight, CAST Imaging, and CodeLogic as direct alternatives, commoditizing code-intelligence buying cycles.
- If CoreStory's specs miss hidden business logic, one failed modernization halts trust and renewals.
What makes CoreStory unique
- CoreStory's September 2025 launch reframed Crowdbotics into legacy-code intelligence, not app-building.
- Its six-phase modernization playbook, released May 2026, embeds human approval gates throughout.
- CoreStory's MCP integrations let Claude Code, Cursor, and Codex query codebase context.
Help us improve and share your feedback! Did you find this helpful?
Benefits
Flexible Work Hours
Remote Work Options
Company Equity
Growth & Insights and Company News
6 month growth
↑ 9%1 year growth
↑ 21%2 year growth
↑ 21%Evermuse + CoreStory: build the right thing, and build it right. Evermuse and CoreStory are partnering to give product and engineering teams (and their AI agents) both halves of the truth: what customers need, and how their code actually works. July 21, 2026 - Evermuse Team Product AI Business Every team that ships software lives with a quiet gap. On one side is what customers actually need, buried in sales calls, interviews, support threads, and feature requests. On the other is how the system actually works: the architecture, the edge cases, the decisions nobody wrote down. AI coding agents have made that gap louder, not quieter. An agent will confidently build the wrong thing, or build the right thing in a way that breaks three things you forgot existed. That's why Evermuse Secure Development Policy is partnering with CoreStory. Two context layers, pointed in opposite directions. CoreStory is a code intelligence platform: a persistent context layer that builds a living understanding of how your codebase actually behaves and serves it to humans and AI wherever product and engineering work happens. Instead of an agent guessing at your architecture, it can query CoreStory for grounded answers about behavior, intent, and impact before it writes a single line. Evermuse is the same idea, pointed the other way. Evermuse Secure Development Policy turn your customer conversations into an always-current picture of what your customers need: searchable evidence, verbatim quotes, competitor intel, and a live, prioritized roadmap your AI can actually reason over. Put plainly: CoreStory is the context layer for your system. Evermuse is the context layer for your customer. Most teams have neither in a form an AI can use. Now you can have both. What the partnership unlocks. Here's where it gets good. Both Evermuse and CoreStory speak MCP, so the same agent (Claude Code, Cursor, Codex, whatever you run) can hold both contexts at once. Picture planning a feature where your agent pulls the three loudest customer pain points from Evermuse, then asks CoreStory which parts of the codebase a fix would touch and what might break. Intent and implementation, in a single pass. You stop choosing between building the right thing and building it right. As part of the partnership, the Evermuse MCP is now available to CoreStory customers through CoreStory's MCP partner directory, and CoreStory is available to Evermuse customers through ours. One connection on each side, and your agents inherit both layers of context. Both halves of the truth. "Great software starts with understanding, of the code and of the customer. Pairing CoreStory's code intelligence with Evermuse's customer evidence gives teams and their agents a complete picture for the first time. We're excited to put it in front of our customers." - Melissa Lyons, Global Director of Channel Sales @ CoreStory The result is fewer round-trips, fewer regressions, and a lot less guessing, from your team and from your AI.
CoreStory, the Code Intelligence company, today announced a $32 million Series A funding round led by Tribeca Venture Partners, NEA, and SineWave Ventures, w...
CoreStory raises $32 million Series A to modernize legacy software with AI. CoreStory, the Code Intelligence company, announced a $32 million Series A funding round led by Tribeca Venture Partners, NEA, and SineWave Ventures, with participation from Harrison Metal, Singtel Innov8, Samsung Next, Nimble Partners, and Alumni Ventures. Enterprises using CoreStory report up to a 50 percent reduction in human development time, turning modernization into a measurable, ROI-positive initiative. The investment accelerates CoreStory's mission to tackle one of enterprise technology's most costly challenges: understanding and modernizing the trillions of lines of legacy code that still power critical systems such as Social Security, Medicare, airlines, banks, and defense networks. Most of this code is undocumented, risky to modify, and too complex for traditional methods to safely modernize. At the same time, a surge of AI-generated code is adding billions of new lines each month, many without documentation or clear design intent. Enterprises now face a dual challenge: modernizing the software they already depend on and managing what AI creates next. CoreStory uses agentic AI to extract business logic and architecture from decades-old applications, transforming opaque systems into living, maintainable assets that organizations can safely expand. Enterprises using CoreStory report up to a 50 percent reduction in human development time by replacing manual discovery, documentation, and validation with automated specifications - turning modernization into a measurable, ROI-positive initiative. "Every time you swipe a card or make a claim, you're depending on software written decades ago that few people understand," said Anand Kulkarni, CEO of CoreStory. "CoreStory's agentic AI reads, maps, and documents that code, turning it into living specifications that make modernization safe and measurable. Our mission is to make the world's software infrastructure understandable again - and future-proof for the AI era." The agentic Code-to-Spec platform. Foundation models excel at generating new code but struggle to reason about large, interconnected systems. CoreStory's Code-to-Spec agent automatically interprets millions of lines of code, converting them into living requirements that developers and AI agents can use like an atlas for code. Research published jointly with Microsoft shows that using CoreStory's structured specifications within AI software-engineering agents improves accuracy by 51 percent, shortening modernization timelines and reducing project risk for enterprise customers. "CoreStory is redefining how enterprises understand and manage their software estates," said Aaron Jacobsen, Partner at NEA. "By converting legacy code into structured, living specifications, CoreStory bridges the gap between decades of accumulated complexity and the new era of AI-assisted development." The rise of Specification-Driven Development. CoreStory pioneers Specification-Driven Development (SDD), a discipline that grounds all software - whether legacy or AI-generated - in explicit, machine-readable specifications expressed in natural language. By recovering specifications from existing systems and embedding them into modern workflows, CoreStory ensures that business intent and technical execution stay aligned throughout the software lifecycle.
CoreStory raises $32M to help companies modernize legacy code with AI. Artificial intelligence startup CoreStory Inc. today announced that it has closed a $32 million funding early-stage round led by Tribeca Venture Partners, NEA and SineWave Ventures. The Series A deal also drew contributions from several other backers. The group included Samsung Next, the venture capital arm of Singaporean internet provider Singtel, Harrison Metal, Nimble Partners and Alumni Ventures. Many large enterprises have decades-old applications written in legacy programming languages such as COBOL. Modernizing those applications often requires rewriting them in a new language. Before developers can begin rewriting a program, they have to create documentation that explains what each of the program's components does and how. Fully documenting an application can take months in some cases. One reason is that legacy software is often written in COBOL, a programming language that relatively few developers understand. Another factor is that some legacy applications include tens of thousands of lines of code or more. San Francisco-based CoreStory is working to speed up the software modernization workflow. The company has developed an artificial intelligence platform, Code-to-Spec, that can automatically generate documentation for legacy code bases. It also provides pointers on how developers should go about modernizing the code. After analyzing a legacy application, Code-to-Spec generates a natural language overview of its features. It also creates a summary of the technologies that power the program. According to CoreStory, Code-to-Spec maps out details such as the programming languages in which a workload is written and the database it uses to store information. Alongside high-level architectural summaries, the platform can generate an explainer of each individual code snippet in an application. The explainer comprises two elements. There's a natural language description, as well as a graph that visualizes the processing steps a given code snippet performs. A chatbot interface enables developers to ask Code-to-Spec questions about an application's code. A user could, for example, request a list of components that could be made more hardware-efficient. Code-to-Spec can rank the code snippets it finds based on the amount of work it would take to rewrite them. The platform not only identifies application components that can be modernized but also provides advice on how to go about the task. For example, Code-to-Spec might suggest that developers equip a code snippet with an error handling mechanism to prevent outages. CoreStory says its platform is powered by model ensembles. A model ensemble is a collection of neural networks that generates multiple answers to each prompt and then combines them into a single response. In some cases, that arrangement can provide higher output quality than other machine learning approaches. ""Every time you swipe a card or make a claim, you're depending on software written decades ago that few people understand," said Chief Executive Officer Anand Kulkarni. "CoreStory's agentic AI reads, maps and documents that code, turning it into living specifications that make modernization safe and measurable." The new funding should put CoreStory in a better position to compete with products such as Anthropic PBC's Claude Code. The programming assistant, which is generating more than $500 million in annualized revenue, lends itself to application modernization projects. Claude Code can rewrite software in a new language and automatically run tests to ensure the code works as expected. A message from John Furrier, co-founder of SiliconANGLE: Support its mission to keep content open and free by engaging with theCUBE community. Join theCUBE's Alumni Trust Network, where technology leaders connect, share intelligence and create opportunities. * 15M+ viewers of theCUBE videos, powering conversations across AI, cloud, cybersecurity and more * 11.4k+ theCUBE alumni - Connect with more than 11,400 tech and business leaders shaping the future through a unique trusted-based network. SiliconANGLE Media is a recognized leader in digital media innovation, uniting breakthrough technology, strategic insights and real-time audience engagement. As the parent company of SiliconANGLE, theCUBE Network, theCUBE Research, CUBE365, theCUBE AI and theCUBE SuperStudios - with flagship locations in Silicon Valley and the New York Stock Exchange - SiliconANGLE Media operates at the intersection of media, technology and AI. Founded by tech visionaries John Furrier and Dave Vellante, SiliconANGLE Media has built a dynamic ecosystem of industry-leading digital media brands that reach 15+ million elite tech professionals. Its new proprietary theCUBE AI Video Cloud is breaking ground in audience interaction, leveraging theCUBEai.com neural network to help technology companies make data-driven decisions and stay at the forefront of industry conversations.
CoreStory announced a $32 million Series A funding round led by Tribeca Venture Partners, NEA, and SineWave Ventures, with participation from others. The investment aims to modernize legacy software using AI for code intelligence. CoreStory's platform reduces human development time by up to 50% by converting legacy code into structured specifications, improving modernization accuracy by 51%. This initiative addresses the challenge of managing both legacy and AI-generated code.