AI Full Stack Engineer

Job Description : AI Fullstack Engineer

Experience : 5+ years

Mode : Remote

Job Responsibilities :

- AI Application Development : Design and build production-grade Generative AI and multi agent systems.

- AI Orchestration : Implement orchestration using LangChain, LangGraph, LlamaIndex, Semantic Kernel, n8n, or custom frameworks.

- LLM Integration : Integrate GPT, Claude, Gemini, and self hosted/open source LLMs.

- RAG Pipelines : Implement Retrieval-Augmented Generation using Pinecone, ChromaDB, Weaviate, pgvector.

- Hybrid Retrieval : Build BM25 + semantic search architectures using ElasticSearch or Solr.

- Prompt Engineering : Develop prompt and context optimization strategies for accuracy, latency, and cost reduction.

- LLM Guardrails : Implement evaluation pipelines, monitoring, observability, and safety checks for LLM systems.

- Multimodal Workflows : Build AI workflows involving text, image, audio, and video modalities.

- Fullstack Frontend : Develop modern front-end applications using React/Next.js, TypeScript, HTML, CSS.

- Backend Engineering : Build modular backend services in Python, JavaScript, or Java.

- Clean Architecture : Apply DDD, SOLID principles, and clean architecture patterns.

- Database Expertise : Work with relational, document, graph, and key value databases.

- Auth Systems : Implement secure OAuth2.0, OIDC, and JWT based authentication.

- SSO Integrations : Integrate Google, Azure AD, Okta, Auth0, Cognito, or enterprise IdPs.

- Event Architectures : Implement event-driven systems using Kafka, MSK, SQS, or equivalents.

- AI Assisted Development : Use tools like Claude Code, GitHub Copilot, Cursor, Codex in structured workflows.

- Workflow Standardization : Build standardized AI-assisted coding workflows and sub agent patterns.

- Innovation Leadership : Lead PoCs, internal R&D, and innovation initiatives.

- Team Mentoring : Mentor engineers in AI system design and best practices.

- Tech Awareness : Stay current with emerging AI models, frameworks, and production trends.

What We are Looking For :

- An engineer who can build end- to- end AI- powered fullstack products, not just prototypes.

- Someone strong in LLM engineering, RAG pipelines, orchestration, and scalable system design.

- A fullstack builder with strong fundamentals in frontend, backend, and cloud-native systems.

- A believer in clean architecture, modular design, and high- quality engineering practices.

- Someone who understands performance, observability, security, and cost-efficient AI deployment.

- A collaborator who works closely with Product, ML, Design, and Platform teams.

- A senior engineer with ownership mindset, architectural depth, and strong mentoring skills.

Skills Set Required :

- 6+ years of software development experience.

- Minimum 2 years of hands- on experience in AI/ML or Generative AI.

- Proven experience deploying production-grade LLM or GenAI systems.

- Strong understanding of LLM internals, prompting, and context optimization.

- Experience building RAG pipelines and using vector databases.

- Strong proficiency in Python, JavaScript, FastAPI, GraphQL.

- Experience with Docker, Kubernetes, and CI/CD pipelines.

- Experience with cloud-native deployments (AWS / GCP / Azure).

- Strong knowledge of scalable microservices and distributed systems.

Bonus : Experience building multi- agent/autonomous systems, Bachelor's or Masters in CS or equivalent.