Senior Full-stack AI Engineer

Job Summary

We are looking for a Senior Full Stack AI Engineer to design, build, and scale AI-powered applications from the ground up. You will bridge the gap between traditional software engineering and modern artificial intelligence. You will craft responsive user interfaces, architect robust backend services, and integrate large language models (LLMs), vector databases, and autonomous agents into seamless production workflows.

Key Responsibilities

• Full-Stack Development: Design and build scalable web applications, including responsive frontends (React, Next.js) and high-performance backends (Python, FastAPI, Node.js).
• AI Agent Integration: Integrate LLMs, small language models (SLMs), and multi-agent workflows via APIs or custom orchestration frameworks.
• Data Knowledge Pipelines: Manage relational databases alongside vector stores to support retrieval-augmented generation (RAG) and real-time context retrieval.
• AI-First UX: Design intuitive user experiences for AI interactions, including streaming responses, intermediate thought outputs, and error handling for non-deterministic AI behavior.
• Deployment Operations: Implement CI/CD pipelines, containerization (Docker, Kubernetes), and monitoring tools to track model performance, latency, and operational costs in production.
• Lead the discussion with business users. Understand what they need, challenge it where needed, and turn it into a clear solution design.
• Set up proper evaluation for every solution. Measure accuracy, cost per request, token usage and response time then improve them.

Required Qualifications

• Experience: 7+ years of professional software development experience, with a strong portfolio of applied AI applications (At least 5+ production deployed use cases).
• Frontend Skills: Proficiency in modern JavaScript/TypeScript, React, or Next.js.
• Backend Skills: Strong command of Python for backend services and API design (FastAPI, Flask).
• AI/ML Knowledge: Hands-on experience with OpenAI, Anthropic, or open-source LLMs, prompt engineering, vector databases (Pinecone, pgvector, Milvus), and RAG pipelines.
• Infrastructure: Working knowledge of cloud platforms (AWS, GCP, or Azure) and container tools like Docker.
• ERP Experience: Prior experience of working in SAP will be a plus

Preferred Skills

• Experience building multi-agent systems or using agent frameworks (LangChain, Langgraph, LlamaIndex)
• Knowledge of MLOps and observability tools (LangSmith, Arize, Prometheus)
• Understanding of fine-tuning or self-hosting smaller open-source models

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.