About Context

We're on a mission to unlock the next frontier of productivity for knowledge workers.

Context AI is building the future of enterprise AI—systems that don't just answer questions or automate simple tasks, but execute the complex, judgment-heavy work that drives real business outcomes. The constraint blocking AI from creating true enterprise value isn't model intelligence anymore; it's institutional intelligence: understanding how your organization operates, where information lives, what quality standards matter, and how work actually gets done.

Our platform solves this by automatically learning each organization's unique context—the tribal knowledge, business rules, internal lexicon, and tacit expertise that defines production-quality work. Each Context task can connect to gigabytes of data across entire codebases, data rooms, and operational systems, enabling AI agents to perform real work that knowledge workers do: engineers analyzing firmware logs to identify root causes, bankers running due diligence on multi-terabyte data rooms, analysts refreshing deliverables with live market data, and consulting teams creating client presentations and websites.

We've proven our system with Fortune 100 customers, achieving 30-40% productivity improvements, reducing cycle times by over 90%, and deploying solutions in days rather than months. Context AI operates 24/7/365 across global teams, freeing knowledge workers to focus on strategic initiatives and new growth frontiers.

Why Context

• Massive Impact: The potential of enterprise AI is unbounded, and we're at the frontier. At Context, you will build software that transforms the nature of work for thousands of engineers, bankers, analysts, consultants, product managers, lawyers, and more

• Real Technical Challenges: Design systems no one else has ever built in order to tackle problems that no one else has ever solved

• Ownership That Matters: We trust our team members to direct influence on product direction and own entire systems. At Context, you propose, build, and ship features with full autonomy and ownership

• Elite Technical Team: We've assembled a superstar team hailing from Apple AI, Microsoft Research, Google, Stripe, Ramp, and more. Work with and learn from the best

What You'll Do

At Context AI, Software Engineers (MTS) build the platform that powers AI agents executing complex, high-stakes work for Fortune 100 enterprises. You'll work at the intersection of frontier language models and production-grade software engineering, creating systems that enable AI to perform production-quality work knowledge workers do every day—not just chat or simple automation.

As an MTS Engineer, you'll architect and build the core product that grounds AI in institutional intelligence—the tribal knowledge, business rules, workflows, and quality standards that define how organizations actually operate. Whether it's building rich editors where AI generates client deliverables, orchestrating agent workflows that analyze million-line codebases, or designing graph-powered context surfaces that feed gigabytes of data to AI systems, you'll use your engineering expertise and product creativity to build software that delivers 30-40% productivity improvements and 90%+ cycle time reductions for our customers.

You'll have direct impact on how enterprises deploy AI across telecommunications, finance, consulting, biotech, and technology. Your code will power AI agents that operate 24/7/365 as continuously improving teammates, executing engineering diagnostics, financial analysis, client deliverable generation, and code shipping with six-figure analyst quality.

As an MTS Engineer, you'll experience the autonomy of a startup with the resources, mentorship, and stability of a well-funded AI company. You'll work in small, agile teams and own end-to-end execution of core platform features, including:

• Architecting and building end-to-end product features that feel magical yet familiar—rich editors, interactive dashboards, multi-modal canvases where AI executes complex work

• Designing Autopilot UX—orchestrating agent plans and live previews so users can see AI think, execute, and iterate in real time with sub-100ms interactions

• Building the integrations layer—seamless connections to Google Workspace, Microsoft 365, Notion, Slack, Linear, and 300+ other tools that ground AI in institutional intelligence

• Engineering the design system & component library—performant, accessible React/Tailwind components that scale from mobile to 4k monitors

• Building the learning flywheel infrastructure—systems that capture subject matter expert feedback and continuously improve AI agent capabilities

• Collaborating on architecture decisions with Product, Design, and Engineering teams to turn customer insights into cross-customer platform capabilities

• Owning full-stack features from database schema to API design to pixel-perfect frontend, ensuring production quality at every layer

Our Stack

• Frontend: TypeScript · React · Next.js · Tailwind CSS

• Backend: Python (FastAPI) · Postgres · Redis · custom graph store

• AI/ML: OpenAI / Anthropic APIs + in-house fine-tunes

• Infrastructure: Kubernetes · GCP

What We Value

• Agency: Innovation happens when team members think from first principles and go above and beyond to achieve objectives—not by simply completing tasks

• Strong Engineering Fundamentals: A highly analytical approach and eagerness to solve technical problems with data structures, distributed systems, cloud infrastructure, APIs, and modern frameworks

• Obsession with Execution Quality: Understanding the difference between AI that assists and AI that executes production-quality work—and building systems that achieve the latter

• Comfort with Ambiguity: Experience or curiosity about working with massive-scale, unstructured data to solve valuable business problems where "how we do things" isn't documented

• Product Creativity: Our engineers don't just turn inputs into outputs. We expect team members to think creatively and invent ways to improve the product

• Low Ego: We understand that the outcome matters more than who gets the credit. Team members share wins and don't play politics

• Adaptive and Introspective: We operate in a fast-moving environment and accordingly iterate rapidly; team members must be able to learn from their mistakes and improve constantly

You Might Be a Fit If

• You've shipped polished, user-loved web apps at scale—front-end to back-end and everything between

• You sweat the details: motion, pixel-perfect layouts, sub-100ms interactions, joyful empty states

• You prototype quickly, validate with users, and iterate based on data and intuition

• You write clear RFCs, welcome feedback, and enjoy pair-designing as much as pair-programming

• Fluent in TypeScript/React; comfortable jumping into Python services when needed (or eager to learn)

• You see AI as a design material and are excited to invent new UX paradigms around it

What We Require

• Relevant experience in software engineering building production web applications

• Strong engineering background, preferred in fields such as Computer Science, Software Engineering, Mathematics, Physics, or related technical disciplines

• Strong full-stack coding skills with proficiency in TypeScript/JavaScript and React; Python experience or willingness to learn

• Experience building production systems—APIs, data pipelines, web applications, real-time UX, or complex frontend architectures

• Track record of shipping features that users love—demonstrated attention to UX, performance, and polish

• Intellectual curiosity about AI/ML systems and their application to real-world problems

Bonus Points

• Experience building collaborative editors (CRDT, OT, multiplayer systems)

• Strong visual design sensibility or prior work with design systems and component libraries

• Publications or medals (IOI/ICPC, NeurIPS, SOSP) showing technical depth

• Familiarity with LLM fine-tuning, retrieval, or agentic chains

• Experience with cloud infrastructure (AWS, GCP, Azure) and modern DevOps practices

• Prior work in high-growth startups or platform/infrastructure teams