Description : Founding AI Full-Stack Engineer I/II Requirements

About Us :

We're building AI that handles the tedious coordination work that drains professionals' time, starting with scheduling. Every day, millions of knowledge workers lose hours to the back-and-forth of coordinating meetings : parsing email threads, juggling time zones, navigating calendar conflicts, and managing the subtle social dynamics of who should flex for whom.

We're creating autonomous AI agents that handle this complexity end-to-end, reasoning through ambiguous situations the way a skilled executive assistant would. Our goal is to give everyone access to the kind of seamless, context-aware support that was previously reserved for executives with dedicated human assistants.

We're in stealth, well-funded, and moving fast.

Position Details :

- Education : Bachelors in Computer Science or Equivalent from IITs

- Employment Type : Full-time position

- Location : Nellore/Chennai

- Work Arrangement : In-Person

Core Responsibilities :

AI & Agent Systems :

- Design, build, and iterate on autonomous AI agents that handle complex, multi-step workflows with minimal human intervention

- Implement robust reasoning systems that handle ambiguity, edge cases, and real-world messiness

- Build evaluation frameworks to measure agent reliability, reasoning quality, and failure modes

Full-Stack Development :

- Own the frontend experience (React, TypeScript) ensuring AI capabilities translate into intuitive UX

- Design and implement backend services and APIs for real-time AI processing

- Build data pipelines that feed context to AI systems while maintaining privacy and security

Infrastructure & Scale :

- Take ownership of system reliability, observability, and performance as we scale

- Implement security best practices for handling sensitive user data and third-party integrations

- Design for growth : architect systems that work at 1K users and evolve gracefully to 1M+

Technical Requirements Essential Technical Skills :

- Deep understanding of GenAI/AI concepts including :

Large Language Models & Prompting : How LLMs work under the hood (attention, tokenization, context windows), prompt engineering patterns, and their failure modes. You should be able to debug why an LLM is producing bad outputs and fix it.

? Embeddings & Vector Search : Practical experience with text embeddings (OpenAI, Cohere, or open-source models), vector databases, and semantic retrieval. Understanding of embedding space geometry, similarity metrics, and when vector search fails.

? Agent Architectures : Familiarity with patterns like ReAct, chain-of-thought, tool use, and multi-agent coordination. Experience with at least one agent framework (LangChain, LangGraph, AutoGen, CrewAI, or similar).

? Evaluation & Reliability : How to measure whether an AI system is working. Experience building eval suites, understanding precision/recall tradeoffs, and debugging non-deterministic systems.

- Power user of AI development tools across multiple categories :

? IDE : Cursor, Windsurf, or similar AI-enhanced development environments

? Development AI : Claude Code, GitHub Copilot, or ChatGPT Codex

? Rapid prototyping : Lovable, v0, or similar website generation tools

- Cloud infrastructure experience with Supabase, and AWS services

- 1-2 years of professional experience (including internships)

- Strong proficiency in TypeScript, Python, and React with demonstrable project experience

Highly Valued : Advanced ML :

- Transformer Architectures : Not just using APIs but also understanding attention mechanisms, positional encoding, fine-tuning approaches, and when to use different model sizes.

- Applied ML at Scale : Experience with feature engineering, model serving, A/B testing ML systems, or handling training/inference at scale.

- Personalization & Learning Systems : Building systems that learn from user behavior : preference learning, recommendation systems, or adaptive interfaces.

- Privacy-Preserving ML : Differential privacy, federated learning concepts, or anonymization techniques for user data.

- NLP Fundamentals : Text classification, named entity recognition, intent detection, sentiment analysis. Understanding of how these fit into production systems.

Highly Valued : Systems & Scale :

- Event-Driven Architecture : Experience with message queues, pub/sub systems, or real-time data pipelines

- Distributed Systems : Understanding of consistency models, failure modes, and designing for reliability

- Performance Optimization : Profiling, caching strategies, and reducing latency in AI-heavy systems

Personal Characteristics & Mindset Who You Are :

- Incredibly inquisitive and fast learner : Your GitHub showcases diverse personal projects across different technologies and domains

- Customer-obsessed product owner : You don't just complete tasks, you ensure features genuinely improve users' lives and continuously iterate based on feedback

- Constructive contrarian : You confidently challenge ideas when you believe there's a better way, but fully commit once decisions are made

- Scale-minded architect : You naturally think about system limits, asking "what happens when we 10x?" and design accordingly from day one

What You'll Work On :

You'll be at the intersection of AI and product, building systems that :

- Reason through ambiguity : Handle open-ended requests where the "right answer" depends on context, relationships, and subtle social dynamics that aren't explicitly stated.

- Learn from behavior : Build preference models that adapt to individual users over time without requiring explicit configuration or onboarding friction.

- Extract patterns from scale : Build ML models that derive insights from behavioral data across thousands of interactions, turning implicit preferences into actionable intelligence.

- Act autonomously with consequences : Operate in the real world with appropriate guardrails, confidence thresholds, and escalation paths that maintain user trust.

- Communicate like humans do : Generate context-aware communication that matches tone, formality, and relationship dynamics naturally.

Why This Matters :

Scheduling seems mundane, but it's a proxy for something bigger : can AI handle open-ended, real-world coordination that requires judgment, not just computation?

Every professional loses hours weekly to administrative coordination. We're building AI that gives that time backnot by automating simple tasks, but by reasoning through the complex ones. If we succeed, we're not just building a scheduling tool; we're proving that AI can handle the ambiguous, context-dependent work that defines white-collar productivity.

You'll be a founding engineer at a company tackling one of the most interesting applied AI problems : teaching machines to handle the messy, human parts of work.