We are looking for a Senior AI Chatbot Engineer who lives at the intersection of conversational design, JavaScript engineering, and applied AI. You are not simply someone who calls an LLM API and wraps it in a chat UI — you are an engineer who understands the nuances of how different large language models behave, when to use each, and how to build chatbot systems that are intelligent, reliable, and genuinely useful to the people who interact with them.In this role, you will design, build, and continuously improve AI-powered chatbot and conversational AI products across multiple LLM providers — including OpenAI, Anthropic, Google Gemini, Mistral, and open-source models. You will own the full chatbot engineering stack: from prompt architecture and context management through to frontend chat interfaces, backend orchestration services, and the evaluation frameworks that keep your bots performing at their best. This is a hands-on senior role for an engineer who loves building things that talk back.

Responsibilities

Chatbot & Conversational AI Engineering

Design, build, and maintain production-grade AI chatbot systems with a focus on accuracy, coherence, and user experience
Architect multi-turn conversation flows, managing context windows, memory, and state across long interactions
Implement variable LLM strategies — selecting and switching between models (e.g. OpenAI GPT-4o, Anthropic Claude, Google Gemini, Mistral, Llama) based on task complexity, latency requirements, cost, and output quality
Build robust prompt engineering frameworks including system prompts, few-shot examples, chain-of-thought patterns, and dynamic prompt construction
Develop fallback, retry, and graceful degradation strategies to handle LLM failures, hallucinations, and edge cases in production

LLM Integration & Orchestration

Integrate and manage multiple LLM provider APIs within a unified orchestration layer, abstracting provider-specific behaviour behind consistent interfaces
Build LLM routing logic that selects the right model for the right task — balancing capability, speed, and cost dynamically at runtime
Implement retrieval-augmented generation (RAG) pipelines to ground chatbot responses in accurate, up-to-date business data
Work with vector databases (e.g. Pinecone, Weaviate, pgvector) and embedding models to power semantic search and knowledge retrieval
Explore and implement agentic chatbot patterns — tool use, function calling, multi-step reasoning, and autonomous task completion

JavaScript & Full Stack Development

Build and maintain chatbot backend services and APIs using Node.js and TypeScript
Develop responsive, real-time chat frontend interfaces using React or Next.js, including streaming token output and markdown rendering
Implement WebSocket and server-sent event (SSE) connections for low-latency, real-time conversational experiences
Integrate chatbot systems with third-party platforms including CRMs, helpdesk tools, knowledge bases, and internal APIs
Manage data persistence for conversation history, user sessions, and chatbot analytics using relational and NoSQL databases

Evaluation, Quality & Safety

Build and maintain chatbot evaluation frameworks to measure response quality, factual accuracy, tone, and task completion rates
Implement guardrails, content filtering, and output validation to ensure safe, on-brand, and policy-compliant chatbot behaviour
Design and run A/B tests across different LLMs, prompts, and conversation flows to drive continuous improvement
Monitor chatbot performance in production with structured logging, latency tracking, and cost observability dashboards
Conduct regular red-teaming and adversarial testing to identify and close failure modes

Collaboration & Iteration

Work closely with product managers, UX designers, and domain experts to define chatbot personas, tone of voice, and conversation flows
Translate complex business requirements into chatbot capabilities, identifying what is achievable with current LLM technology and what requires custom solutions
Mentor junior engineers on LLM engineering patterns, prompt design, and conversational AI best practices
Stay current with the rapidly evolving LLM landscape and bring new models, techniques, and tools into the team's practice
Document chatbot architectures, prompt libraries, evaluation results, and operational runbooks

Experience and education

Required

5–8 years of professional software engineering experience, with significant focus on AI, chatbot, or conversational system development
Demonstrated hands-on experience building production chatbots or conversational AI products using multiple LLM providers
Deep proficiency in JavaScript and TypeScript, with strong Node.js backend and React frontend skills
Proven expertise in prompt engineering — including system prompt design, few-shot prompting, chain-of-thought, and dynamic prompt construction
Experience managing multi-turn conversation context, including context window limitations across different models
Practical experience with RAG architectures, vector databases, and embedding-based retrieval
Familiarity with at least three major LLM providers and their respective APIs, strengths, and trade-offs (e.g. OpenAI, Anthropic, Google, Mistral, Cohere)
Experience building real-time streaming interfaces using WebSockets or SSE
Solid understanding of REST and GraphQL API design and integration patterns

Preferred

Experience implementing LLM routing or model selection logic across variable provider backends
Hands-on experience with orchestration frameworks such as LangChain, LangGraph, LlamaIndex, or Vercel AI SDK
Familiarity with open-source and self-hosted LLMs (e.g. Llama 3, Mistral, Falcon) and inference serving (e.g. Ollama, vLLM, HuggingFace TGI)
Experience designing and running structured chatbot evaluation pipelines (e.g. using RAGAS, LangSmith, or custom eval frameworks)
Background in conversational UX design principles and dialogue system design
Experience with function calling, tool use, and agentic chatbot architectures
Familiarity with Databricks or similar platforms for managing the data that powers chatbot knowledge bases
Experience in customer-facing chatbot deployments in regulated or high-stakes environments (fintech, healthcare, legal)

Education

The following qualifications are accepted for this role:

Bachelor's degree in Computer Science, Software Engineering, Artificial Intelligence, Computational Linguistics, or a closely related field
Bachelor's degree in a non-technical discipline combined with a recognised software engineering or AI bootcamp and a demonstrable portfolio of chatbot or conversational AI projects
Associate's degree with 7+ years of directly relevant AI chatbot or conversational systems engineering experience
No formal degree with 8+ years of demonstrated experience building and shipping production AI chatbot systems, evidenced by a strong portfolio

Certifications (Advantageous)

DeepLearning.AI — Large Language Models or Generative AI specialisation
OpenAI or Anthropic developer certifications (where available)
AWS Certified Machine Learning – Specialty
Google Professional Machine Learning Engineer
Databricks Certified Machine Learning Associate
Microsoft Certified: Azure AI Engineer Associate