Overview
The R&D Engineer is a researcher-practitioner - someone equally comfortable reading papers and shipping prototypes. They are responsible for staying close to the frontier of LLM and AI systems research, identifying ideas with practical value, and building POCs that demonstrate feasibility. These POCs are demoed to the team and, where validated, handed off to the Platform and AI Engineers to productionize. This person does not work in isolation — they collaborate closely with the rest of the team throughout the research-to-product pipeline.

What You'll Do:

• Monitor and synthesize developments in LLM systems, AI infrastructure, and adjacent research areas
• Prototype and evaluate novel ideas with a fast feedback loop — build, demo, iterate
• Extend and improve the existing agent and RAG SDKs with new retrieval strategies, agent patterns, and provider integrations
• Evaluate new embedding models, reranking approaches, and retrieval architectures against the existing pipeline
• Collaborate with the Platform and AI Engineers to hand off validated POCs
• Produce clear documentation and demos that make research accessible to non-researchers
• Contribute to discussions with the tech lead on long-term research direction and where to place technical bets
• Engage with the broader research community — conferences, papers, open-source projects
• Identify opportunities where emerging techniques can address real problems surfaced by the AI Engineer

What You Bring:

• Hands-on experience building or evaluating LLM systems — fine-tuning, inference, retrieval, or agents
• Familiarity with RAG architectures beyond naive vector search — HyDE, MMR, graph-based retrieval, reranking, or hybrid search
• Exposure to agent frameworks and multi-agent orchestration patterns (PydanticAI, LangGraph, AutoGen, CrewAI, or similar)
• Demonstrated ability to move quickly from idea to working prototype
• A portfolio of explored ideas — published work, technical blog posts, side projects, or OSS contributions
• Strong communication skills — can explain complex research to non-researchers clearly
• Collaborative by default; understands that research value is realized when ideas ship
  • Core: Python, agent frameworks (PydanticAI or equivalent), RAG pipeline design (embedding, retrieval, reranking), managed ML platforms (Vertex AI or equivalent)
  • Nice to have: Systems-level programming experience, familiarity with inference infrastructure (vLLM, TensorRT), experience with RLHF or fine-tuning pipelines, MCP protocol, graph databases (Neo4j)

#LI-JH

#LI-Remote

ROLE OVERVIEW:

As a Full-Stack Developer, you will architect and build custom web applications across multiple client engagements, owning both the backend API layer and the frontend. A defining aspect of this role is working with AI as a logic layer within applications: integrating LLM APIs for validation, decision-making, classification, and content generation. You make strong technical decisions around authentication, security, state management, and performance, and you bring cloud engineering awareness for edge computing, CDN delivery, and serverless environments. This is not a traditional manual coding role. You orchestrate AI development tools, primarily Claude Code, through strategic prompting and rigorous review, taking full ownership of what ships.

RESPONSIBILITIES

Your key responsibilities will include:

• Architect and build custom web applications using Node.js (Nest.js, Express, Hono), Python (FastAPI, Flask), and Next.js/React.
• Design and build RESTful and/or GraphQL APIs that serve multiple frontends and integrate with third-party services.
• Integrate AI and LLM APIs as a core logic layer, building intelligent features such as validation, classification, content generation, and decision support.
• Implement authentication, authorisation (JWT, OAuth, RBAC), and security across applications.
• Design and manage database layers (PostgreSQL, MongoDB, cloud-managed equivalents), including schema design, migrations, and query optimisation.
• Architect with cloud-native patterns: edge functions, CDN configuration, serverless deployments, and caching strategies.
• Write and maintain automated tests across the full stack: unit (Vitest/Jest), API/integration, component (React Testing Library), and E2E (Playwright/Cypress).
• Orchestrate AI development tools (Claude Code) through strategic prompting, ensuring high-quality, production-ready output.

EXPERIENCE

The ideal candidate will have:

• Strong backend proficiency across Node.js (Nest.js, Express, Hono) and Python (FastAPI, Flask), with TypeScript and Python as working languages.
• Strong Next.js and React experience.
• Experience integrating AI/LLM APIs as an application logic layer: validation, classification, content generation, and decision-making within business workflows.
• Database design and management: PostgreSQL, MongoDB, cloud-managed services (Cloud SQL, RDS, ApsaraDB).
• Authentication and authorisation patterns (JWT, OAuth, RBAC) and API security.
• Cloud engineering: edge functions, CDN configuration, serverless architecture, container orchestration.
• Full-stack test automation: unit, API/integration, component, and E2E testing.
• Performance optimisation: caching, query optimisation, code splitting, monitoring.
• REST and/or GraphQL API design.
• Demonstrated ability to orchestrate AI development tools through strategic prompting and quality oversight.

TECHNOLOGIES

Deep understanding of the following technologies is essential:

• Node.js, TypeScript, Nest.js, Express, Hono, Python, FastAPI, Flask.
• Next.js, React, Tailwind CSS.
• PostgreSQL, MongoDB, cloud-managed database services.
• Authentication: JWT, OAuth, RBAC.
• Cloud and edge: Alibaba Cloud, GCP, AWS, Cloudflare Workers, Vercel Edge, Lambda.
• AI/LLM API integration and orchestration.
• Testing: Vitest/Jest, React Testing Library, Playwright/Cypress, API testing.
• Docker, CI/CD, Git, Claude Code.

PREFERRED QUALIFICATIONS

• Experience in a consulting or agency environment across multiple concurrent client engagements.
• Apollo GraphQL Server for federated or schema-first APIs.
• Event-driven patterns (webhooks, message queues, real-time notifications).
• Multi-model AI strategies (routing between LLMs based on task requirements).
• Graph databases (Neo4j) or vector databases (pgvector, Pinecone).
• Infrastructure as Code (Terraform, Pulumi).
• Export/print workflows (PDF generation, report exports).

WHO YOU ARE

You are a full-stack developer who takes ownership of the complete application, from API design and database schema through to the frontend. You treat security, performance, and data integrity as first-class concerns. You are comfortable working with AI as a logic layer, and you understand cloud-native architecture well enough to make informed decisions about edge computing, caching, and deployment. You thrive in a consulting environment, adapting to new domains and communicating clearly with technical teams and client stakeholders.

WHAT APPNOVATION HAS TO OFFER 

• Challenging and rewarding work with real impact
• Direct Access to Cutting-Edge AI Platforms
• Diverse and Inclusive Culture 
• Growth opportunities for personal and professional development
• A collaborative and innovative work environment where your ideas are valued
• Exposure to exciting projects and high-profile clients
• Supportive work environment with access to company leaders
• Hybrid working model

ROLE OVERVIEW:

As a Full-Stack Developer, you will architect and build custom web applications across multiple client engagements, owning both the backend API layer and the frontend. A defining aspect of this role is working with AI as a logic layer within applications: integrating LLM APIs for validation, decision-making, classification, and content generation. You make strong technical decisions around authentication, security, state management, and performance, and you bring cloud engineering awareness for edge computing, CDN delivery, and serverless environments. This is not a traditional manual coding role. You orchestrate AI development tools, primarily Claude Code, through strategic prompting and rigorous review, taking full ownership of what ships.

RESPONSIBILITIES

Your key responsibilities will include:

• Architect and build custom web applications using Node.js (Nest.js, Express, Hono), Python (FastAPI, Flask), and Next.js/React.
• Design and build RESTful and/or GraphQL APIs that serve multiple frontends and integrate with third-party services.
• Integrate AI and LLM APIs as a core logic layer, building intelligent features such as validation, classification, content generation, and decision support.
• Implement authentication, authorisation (JWT, OAuth, RBAC), and security across applications.
• Design and manage database layers (PostgreSQL, MongoDB, cloud-managed equivalents), including schema design, migrations, and query optimisation.
• Architect with cloud-native patterns: edge functions, CDN configuration, serverless deployments, and caching strategies.
• Write and maintain automated tests across the full stack: unit (Vitest/Jest), API/integration, component (React Testing Library), and E2E (Playwright/Cypress).
• Orchestrate AI development tools (Claude Code) through strategic prompting, ensuring high-quality, production-ready output.

EXPERIENCE

The ideal candidate will have:

• Strong backend proficiency across Node.js (Nest.js, Express, Hono) and Python (FastAPI, Flask), with TypeScript and Python as working languages.
• Strong Next.js and React experience.
• Experience integrating AI/LLM APIs as an application logic layer: validation, classification, content generation, and decision-making within business workflows.
• Database design and management: PostgreSQL, MongoDB, cloud-managed services (Cloud SQL, RDS, ApsaraDB).
• Authentication and authorisation patterns (JWT, OAuth, RBAC) and API security.
• Cloud engineering: edge functions, CDN configuration, serverless architecture, container orchestration.
• Full-stack test automation: unit, API/integration, component, and E2E testing.
• Performance optimisation: caching, query optimisation, code splitting, monitoring.
• REST and/or GraphQL API design.
• Demonstrated ability to orchestrate AI development tools through strategic prompting and quality oversight.

TECHNOLOGIES

Deep understanding of the following technologies is essential:

• Node.js, TypeScript, Nest.js, Express, Hono, Python, FastAPI, Flask.
• Next.js, React, Tailwind CSS.
• PostgreSQL, MongoDB, cloud-managed database services.
• Authentication: JWT, OAuth, RBAC.
• Cloud and edge: Alibaba Cloud, GCP, AWS, Cloudflare Workers, Vercel Edge, Lambda.
• AI/LLM API integration and orchestration.
• Testing: Vitest/Jest, React Testing Library, Playwright/Cypress, API testing.
• Docker, CI/CD, Git, Claude Code.

PREFERRED QUALIFICATIONS

• Experience in a consulting or agency environment across multiple concurrent client engagements.
• Apollo GraphQL Server for federated or schema-first APIs.
• Event-driven patterns (webhooks, message queues, real-time notifications).
• Multi-model AI strategies (routing between LLMs based on task requirements).
• Graph databases (Neo4j) or vector databases (pgvector, Pinecone).
• Infrastructure as Code (Terraform, Pulumi).
• Export/print workflows (PDF generation, report exports).

WHO YOU ARE

You are a full-stack developer who takes ownership of the complete application, from API design and database schema through to the frontend. You treat security, performance, and data integrity as first-class concerns. You are comfortable working with AI as a logic layer, and you understand cloud-native architecture well enough to make informed decisions about edge computing, caching, and deployment. You thrive in a consulting environment, adapting to new domains and communicating clearly with technical teams and client stakeholders.

WHAT APPNOVATION HAS TO OFFER 

• Challenging and rewarding work with real impact
• Direct Access to Cutting-Edge AI Platforms
• Diverse and Inclusive Culture 
• Growth opportunities for personal and professional development
• A collaborative and innovative work environment where your ideas are valued
• Exposure to exciting projects and high-profile clients
• Supportive work environment with access to company leaders
• Hybrid working model