Senior Software Engineer (AI & Python) - 61916816384

Schedule: Flexible hours with at least 75% overlap with U.S. Eastern Time. We support a standard ET workday and are open to shifted schedules (e.g., 6:00 AM-3:00 PM ET, 9:00 AM-6:00 PM ET, or 12:00 PM-9:00 PM ET) as long as overlap is maintained., In practice, that means we sit between developers, their coding agents, and production: enforcing each team’s functional and security standards, surfacing issues in real time, and continuously improving the specifications that keep agents on track. We are early, well-positioned in a fast-moving category, and building the foundational systems that the product will run on for years.

About The Role

This is a foundational engineering hire on an AI-first team. You will help build the core systems that power our AI review and analysis engine - the LLM and NLP pipelines that interpret code, the multi-agent systems and retrieval layers behind them, and the APIs and services that deliver results to users and agents.

The role exists because the heart of our product is hard, specialized AI engineering: reasoning over code with LLMs and agents, building reliable systems on top of inherently probabilistic models, and doing it with the rigor expected of a security product. We work AI-first internally too - every engineer uses frontier AI tooling daily and is expected to improve how we use it. You will work closely with the founder, own significant pieces of the architecture end to end, and make decisions that shape how the platform scales. Titles matter less here than competence and ownership., AI & LLM Engineering

• Build and integrate LLM-powered features into the product, from prototyping through production.
• Develop NLP and retrieval pipelines using LangChain, vector databases, and the broader Python AI ecosystem (Pandas, NumPy, and similar).
• Design and reason about multi-agent systems, anticipating how small changes ripple through a probabilistic, AI-first system.
• Translate research-style approaches into reliable, maintainable production systems.

Working AI-First

• Make heavy, daily use of AI in your own engineering workflow - we provide top-tier tooling (e.g., Claude Max 20x, ChatGPT Pro 20x).
• Regularly use and contribute to our internal skills, agent integrations, and agentic loops, raising the quality of their outputs across our software development, testing, and documentation use cases.

Data Modeling & Storage

• Work with vector databases to power retrieval and AI-driven features.
• Store and manage data in NoSQL/document databases (e.g., MongoDB or similar).
• Make sound decisions about data structure, performance, and scalability.

APIs & Services

• Design, build, and consume GraphQL and REST APIs.
• Contribute to a microservices-oriented architecture within a monorepo environment.

Engineering Quality & Practices

• Maintain a high bar for code quality through detailed peer review.
• Own testing across unit, integration, and end-to-end layers.
• Work within CI/CD pipelines and contribute to keeping them healthy.
• Document your work clearly using markdown and inline comments so others can build on it., * Comfortable in an early-stage environment - you move quickly, make pragmatic tradeoffs, and are energized by building foundational systems rather than maintaining mature ones.
• A clear communicator and strong documenter - you leave behind work others can understand and extend.
• Rigorous by instinct - testing, peer review, and clean data design are how you naturally operate, not chores.
• AI-native - you already work AI-first, have informed opinions about how to get the best out of frontier models and agents, and stay close to how the field is moving.

Why Join Us

• Build at the frontier of AI and software security, on a product solving a problem that is growing fast across the industry.
• High autonomy and high impact - your decisions will shape the core of the platform.
• Direct collaboration with the founder and a small, senior team.
• We provide and continually invest in top-tier AI tooling for every engineer (e.g., Claude Max 20x, ChatGPT Pro 20x) - you will work with the best models available.
• Fully remote with flexible hours, structured around meaningful overlap with the U.S. team.

• 5+ years of professional software engineering experience. Many strong candidates for this role will have 10+ years; we weigh demonstrated competence over years.
• Expert-level proficiency in Python. This is the primary language of the role and is non-negotiable.
• A genuine foundation in AI beyond the surface level - you can explain how inference works and reason from first principles, so you can logic through how small changes affect behavior in an AI-first system. Critical to the work.
• Intimate knowledge of vectors and vector databases. Critical to the work.
• Hands-on experience designing or working with multi-agent systems. Critical to the work.
• Practical, hands-on experience building with LLMs, including LangChain and the supporting Python AI ecosystem (Pandas, NumPy, and similar). Critical to the work.
• Daily, fluent use of AI in your own workflow, plus the habit of improving it - regularly using and contributing to internal skills, agent integrations, and agentic loops.
• Experience with NoSQL/document databases (MongoDB or similar).
• Comfort designing and consuming both GraphQL and REST APIs.
• Proficiency with Git. Non-negotiable - it is the de facto standard for how we work.
• Familiarity across modern development practices: detailed peer review, unit/integration/end-to-end testing, microservices, monorepos, and CI/CD pipelines.
• Strong written communication and a genuine willingness to document processes thoroughly.
• Ability to maintain at least 75% daily overlap with U.S. Eastern Time.

Preferred Qualifications

• Familiarity with Go (Golang). Not required - a nice-to-have for occasional tasks alongside Python.
• Exposure to security, developer tooling, or AI agent / coding-agent products.
• Prior experience as an early or foundational engineer at a startup.

We are a rapidly growing U.S.-based software company building AI guardrails for modern engineering teams. As organizations adopt AI coding agents, they ship faster - but also introduce security vulnerabilities, business-logic flaws, and standards drift that traditional tooling misses. Our platform solves this by combining LLM-powered review with deterministic analysis to govern, secure, and add observability to AI-generated code across an entire team’s tools and agents.