Job description

This role is focused on experienced, hands-on engineers who can take end-to-end ownership of complex full-stack systems—spanning TypeScript, React, Node.js, and generative AI integrations—and operate effectively in a fast-moving, early-stage environment. You will be expected to translate ambiguous product goals into reliable, scalable solutions, contribute directly to core platform architecture, and collaborate closely with product, design, and leadership to deliver real-world AI capabilities used in production by customers.

Job requirements

• Hands-on implementation of LLM-powered systems (applications, agents, workflows).

• Experience with RAG, embeddings, vector search, or evaluation methodologies.

• Familiarity with tool/agent orchestration frameworks (LangChain, LangGraph, LlamaIndex, custom frameworks, etc.).

• Understanding of model behaviour, prompting strategies, and practical guardrail patterns.

• Strong programming ability in TypeScript, React, Node.js 

• Experience building user-facing and backend systems end-to-end.

• Ability to contribute across the entire stack without needing months of ramp-up.

• 5–10+ years professional engineering experience (typically senior-level).

• Strong architecture, debugging, and performance optimization skills.

• Familiarity with OpenTelemetry, distributed systems, eventing, or cloud-based observability concepts.

 Nice to Have:

• Exposure to evaluation frameworks, safety systems, or LLM traceability.

• Experience with Python for AI workflows or backend services.

• Experience with data pipelines, vector databases, or scalable ML infrastructure.

• Contributions to open-source AI frameworks (LangChain, LlamaIndex, Transformers, etc.)

Job responsibilities

• Design, implement, and ship production-grade Gen AI capabilities.

• Build full-stack product features using TypeScript, React, Node.js, and modern tooling.

• Contribute to the development of our observability and AI-tracing systems 

• Build internal frameworks and reusable components that accelerate GenAI feature delivery.

• Take end-to-end ownership of features—from requirements shaping through implementation, testing, release, and iteration.

• Operate autonomously in ambiguity, making pragmatic engineering decisions aligned with product goals.

• Diagnose and improve performance, reliability, and quality of AI-driven systems.

• Partner closely with Product, Design, and other Engineers to shape solutions.

• Participate actively in code reviews, architectural discussions, and internal technical debates.

Job benefits

• Fully remote, work from home environment

• Employee Share Option Plan

• Flexible working hours

• Paid Time-Off

• Periodic in-person offsites globally (travel permitting)

• Continued education support

• Advancement opportunity