Requirements
- Minimum 5 years of full stack development experience
- At least 1 year of hands-on experience with LLMs and AI systems
- Strong backend skills: Node.js, Python or equivalent; API design, database systems, distributed architectures
- Frontend expertise: JavaScript/TypeScript, React or Vue, browser extensions, embeddable widgets
- Ability to design scalable, fault tolerant AI systems with performance and cost in mind
- Experience with prompt engineering, RAG, vector databases, embeddings, and semantic search
- Familiarity with AI operations: prompt versioning, A/B testing, monitoring agent behavior
- High ownership and problem-solving ability in fast-paced startup environments
- Founding engineer mindset: self-driven, proactive, and can figure things out independently
Responsibilities
- Build scalable backend services for AI agent orchestration (LLM integration, prompts, context management)
- Design robust AI pipelines with RAG, tool calling, and chain of thought reasoning
- Create frontend experiences: chat UIs, Chrome extensions, embeddable widgets, third-party integrations
- Optimize LLM usage: token management, caching, latency and cost efficiency
- Implement observability for agents: prompt versioning, QA pipelines, analytics
- Contribute to infrastructure decisions: model selection, vector DBs, real-time capabilities
- Stay updated with AI trends and integrate relevant new techniques
Job Details
Location: Bengaluru, India
Work Mode: In-person (6 days a week)
Interview process
- Culture Fit Screening
- Technical Screening
- Assignment
- Technical Round: DSA and System Design
