Software Engineer

As a Software Engineer - AI and Backend at Nurix AI, you will build the backend systems and AI-powered infrastructure that power our next-generation conversational agents. You will work at the intersection of backend engineering, LLMs, AI agents, real-time systems, and enterprise integrations.

You will design and develop scalable APIs, data pipelines, orchestration layers, and AI/LLM integrations that enable intelligent agents to reason, take actions, interact with enterprise systems, and continuously improve from real-world interactions. This role is ideal for engineers who have strong backend fundamentals and are excited about building production-grade AI systems, conversational AI platforms, agentic workflows, and real-time applications.

Responsibilities:

• Human-like, goal-driven conversational agents without rigid, prescriptive workflows.
• AI agent orchestration and backend systems for reasoning, tool usage, and enterprise workflows.
• Self-learning and feedback loops that improve agent performance using interactions and historical transcripts.
• Real-time AI systems capable of interacting with GUIs, browsers, APIs, and external tools.
• Human-in-the-loop workflows including escalations, approvals, and agent copilots.
• Scalable backend services that connect LLMs and AI models with enterprise applications.
• Data ingestion, processing, and orchestration pipelines supporting AI/ML workloads.

AI and LLM Engineering:

• Build and integrate LLM-powered applications, conversational AI systems, and AI agents into production environments.
• Develop backend services for LLM orchestration, prompt execution, tool calling, context management, and agent workflows.
• Integrate AI models from providers such as OpenAI, Anthropic, Google, Azure OpenAI, or similar platforms.
• Work with RAG, embeddings, vector databases, prompt engineering, and AI evaluation workflows.
• Build systems that enable AI agents to interact with APIs, browsers, enterprise applications, and external tools.
• Develop feedback and learning loops using conversation history, user interactions, and agent performance data.
• Collaborate with AI/ML engineers to productionize models and AI workflows with a focus on latency, reliability, scalability, and cost efficiency.

Backend Development:

• Design and implement high-performance, scalable backend services and REST APIs using Python and/or Node.js .
• Build microservices and orchestration layers that connect AI models with enterprise applications and workflows.
• Develop robust APIs for conversational AI, agent execution, data processing, and third-party integrations.
• Design data ingestion and processing pipelines for large-scale, data-intensive AI applications.
• Work with SQL and NoSQL databases, caching systems, queues, and event-driven architectures.
• Build asynchronous and real-time systems using technologies such as WebSockets, message queues, streaming, or event-driven architectures.
• Optimise backend systems for high throughput, low latency, reliability, security, and scalability.
• Write clean, maintainable, well-tested, production-quality code.

AI Infrastructure and Integration:

• Build infrastructure and services required to deploy and operate AI-powered applications at scale.
• Integrate AI/ML workflows with enterprise systems, APIs, databases, and internal platforms.
• Work closely with AI/ML and infrastructure teams to improve model serving, inference performance, observability, and reliability.
• Contribute to MLOps/LLMOps workflows, including model monitoring, evaluation, experimentation, and production deployment.
• Troubleshoot complex issues across AI models, backend services, integrations, and distributed systems.

Frontend and Product Integration:

• Collaborate with frontend engineers to build intuitive interfaces for AI-powered products and dashboards.
• Contribute to frontend development using React, Next.js, or similar frameworks when required.
• Build seamless product experiences connecting AI agents, backend services, and enterprise users.

Requirements:

• 4+ years of software engineering experience, with strong experience in backend development.
• Strong proficiency in Python and/or Node.js .
• Strong experience building REST APIs, microservices, and scalable backend systems.
• Hands-on experience integrating AI/ML models, LLMs, or conversational AI into production applications.
• Strong understanding of LLM application development, AI agents, prompt engineering, RAG, embeddings, or LLM orchestration.
• Experience with SQL and/or NoSQL databases.
• Experience with asynchronous programming, event-driven systems, WebSockets, message queues, or real-time architectures.
• Experience with cloud platforms such as AWS, GCP, or Azure.
• Experience with Docker and containerised applications; Kubernetes knowledge is a plus.
• Familiarity with vector databases such as Pinecone, Weaviate, Qdrant, Milvus, ChromaDB, or similar.
• Exposure to MLOps/LLMOps, model evaluation, monitoring, or AI observability.
• Good understanding of system design, scalability, security, and distributed systems.
• Experience working with data-intensive or AI-powered applications.
• Strong problem-solving and debugging skills.
• Ability to work in a fast-paced startup environment and collaborate closely with AI/ML, product, and infrastructure teams.

Good to Have:

• Experience with LangChain, LangGraph, LlamaIndex, Semantic Kernel, or similar AI frameworks.
• Experience building agentic AI or multi-agent systems.
• Experience with function/tool calling and MCP (Model Context Protocol).
• Experience with OpenAI, Anthropic Claude, Gemini, Azure OpenAI, or Vertex AI.
• Experience with Redis, Kafka, RabbitMQ, Celery, or similar distributed systems technologies.
• Familiarity with Langfuse, MLflow, or other AI/LLM observability and evaluation platforms.
• Experience building enterprise conversational AI, copilots, or intelligent automation platforms.
• Experience with browser automation, computer-use agents, or GUI interaction systems.

Collaboration and Culture:

• Work closely with AI/ML engineers, backend engineers, product managers, and architects.
• Participate in architecture discussions, design reviews, code reviews, and technical decisions.
• Take ownership of features from design through production deployment.
• Thrive in a fast-paced, high-growth environment where engineering, AI research, and product development closely intersect.
• Contribute to engineering best practices, coding standards, testing, observability, and system reliability.