Role Overview
We are building systems that operate beyond prompt‑wrapping and API‑gluing.
This role is for someone who understands how to design real AI systems, not UI skins over someone else’s model.
You will work across agentic AI, distributed systems, data engineering, and operational scaling. Expect to build adapters, not wait for documentation.
Core Responsibilities
1. AI Systems & Distributed Architecture
- Design and deploy stateless, serverless systems using AWS Lambda, S3, DynamoDB, and event-driven patterns.
- Build custom agentic logic using LangChain, AutoGen, or equivalent frameworks.
- Integrate agents with persistent memory systems (e.g., vector DB + custom memory layer).
- Implement RAG pipelines, local LLM execution, and cost‑optimized inference strategies.
- Architect systems that scale horizontally and degrade gracefully under load.
2. Data Engineering & Intelligence Extraction
- Build ingestion pipelines for lab data, formulation data, and structured/unstructured datasets.
- Implement vector databases (ChromaDB, Pinecone, Weaviate) for semantic search and knowledge extraction.
- Create internal tools that convert raw scientific data (e.g., UHPLC outputs, ingredient metadata) into actionable intelligence.
3. Product Engineering & Frontend
- Develop minimal, high‑performance frontends using React.js and modern build tools.
- Implement SSR, hydration optimization, and JSON‑LD schema for SEO-critical products.
- Build internal dashboards, agent consoles, and operational UIs with zero unnecessary dependencies.
4. Operations & Business Support
- Assist with hiring workflows, vendor evaluation, and ERPNext data operations when needed.
- Maintain and evolve SOPs for engineering, deployment, and operational continuity.
- Work directly with the founder to unblock technical and operational bottlenecks.
Technical Requirements
- Strong proficiency in JavaScript (ES6+) and Python (FastAPI/Flask).
- Deep understanding of cloud-native architecture, serverless patterns, and distributed systems.
- Experience with vector databases, embeddings, and retrieval pipelines.
- Familiarity with local LLM execution, quantization, and GPU/CPU optimization.
- Ability to design systems with fault tolerance, sharding, and zero-trust principles.
- Comfortable working across frontend, backend, infra, and AI pipelines.
Mindset Requirements
- You prefer building foundational systems over stitching APIs.
- You enjoy solving undefined problems and designing your own abstractions.
- You think in terms of scalability, failure modes, and long-term maintainability.
- You can switch between deep engineering and operational tasks without friction.
- You take ownership of outcomes, not tasks.
Work Location: Remote
