Full Stack Engineer - Artificial Intelligence

Job Description :

Were looking for engineers who build AI into the core of systems, not just layer it on top.

In this role, you will design and ship full-stack applications where LLMs, retrieval pipelines, and agentic workflows are first-class architectural components.

The work focuses on production-grade AI systems, requiring a deep understanding of latency, failure modes, context limits, and prompt reliability.

This role is ideal for engineers who have experience working with real-world AI deployments and care about how models behave beyond demos.

Roles and Responsibilities :

- Design and build full-stack features where LLMs, agents, or ML inference are core components

- Own end-to-end development from prompt design and context engineering to APIs and UI rendering

- Architect RAG pipelines, tool-use chains, and multi-step agent workflows for production environments

- Make decisions on model selection, chunking strategies, retrieval tuning, and output validation

- Implement AI safety practices including hallucination detection, validation layers, and graceful degradation

- Build scalable frontends using React or Next.js and backends using Node.js or Python

- Design clean, versioned APIs and well-structured data schemas

- Integrate vector databases, document stores, and third-party LLM APIs efficiently

- Ensure observability through logging, latency tracking, token usage monitoring, and error tracing

- Write clean, testable, and well-documented code with consistent CI/CD practices

- Participate in client-facing architecture discussions and technical decision-making

- Translate ambiguous product requirements into clear technical solutions with defined trade-offs

- Demo working software to non-technical stakeholders with clarity and focus on outcomes

Skills :

- Hands-on experience with LLM APIs such as OpenAI, Anthropic, or Gemini

- Strong understanding of embeddings, RAG architectures, and agent-based systems

- Familiarity with frameworks like LangChain, LlamaIndex, or similar tools

- Strong frontend skills in React and TypeScript

- Backend experience in Node.js and/or Python frameworks such as FastAPI, Django, or Flask

- Experience working with vector databases like Pinecone, Weaviate, or pgvector

- Strong understanding of system reliability including failure handling, fallbacks, and cost optimization

- Ability to work in consulting environments with multiple clients and evolving priorities

- Strong communication skills, both written and verbal

- Habit of staying updated with AI advancements and applying them effectively

What You Will Build :

- AI powered enterprise applications with real-world usage and high reliability requirements

- Internal copilots to enhance productivity and workflows

- Intelligent document processing and automation systems

- Agent-driven multi-step automation solutions

- Data-grounded decision-making tools for enterprise use cases

- Systems deployed across industries such as financial services, healthcare, and technology

- Production systems where performance, reliability, and user experience directly impact business

outcomes