AI Engineer — Chatbot & Agentic AI

Location: Doha, Qatar

Department: Tech

Experience: 5+

• Own the end-to-end architecture of Snoonu's conversational AI and agentic automation platform — from LLM selection and prompt strategy to cloud infrastructure and observability.
• Define engineering standards, design patterns, and best practices for AI system development; conduct design reviews and enforce quality bars.
• Mentor and guide junior/mid-level engineers; review code, provide technical feedback, and accelerate the team's LLM engineering capabilities.
• Partner directly with the R&D Director to evaluate emerging technologies, shape the team's technical roadmap, and present recommendations with trade-off analysis.

• Lead the design and delivery of multi-channel chatbots (web, WhatsApp, app) using AWS Lex, Bedrock, and API Gateway integrated with Claude or other LLMs.
• Own complex dialogue system challenges: multi-turn reasoning, context persistence, intent disambiguation, and graceful fallback strategies.
• Integrate chatbots with Snoonu's backend services (order management, CRM, logistics APIs) via secure, scalable RESTful/event-driven patterns.
• Drive LLM evaluation cycles — benchmark model versions, prompt strategies, and RAG configurations against production quality and cost targets.

• Architect Agentic AI systems that encode Snoonu SOPs as autonomous, multi-step workflows for customer support, order verification, and logistics operations.
• Select and govern the right orchestration approach (LangGraph, CrewAI, Bedrock Agents, Step Functions) per use case — with a clear rationale on reliability, debuggability, and scalability.
• Design robust memory, context management, tool-use, and guardrail layers to ensure agents behave predictably in adversarial or edge-case conditions.
• Establish human-in-the-loop checkpoints, confidence thresholds, and escalation paths — ensuring agents augment rather than replace human judgment in critical decisions.

• Design and own the cloud backbone for AI services: Lambda, ECS/Fargate, SQS/SNS, DynamoDB, S3, CloudWatch, and Bedrock — with a focus on scalability, cost, and reliability.
• Build CI/CD pipelines for prompt versioning, model rollout, A/B testing, and automated evals before production deployment.
• Define and enforce monitoring standards for drift, latency, cost, and failure rates across all deployed AI systems.

• Lead frontier model evaluation — benchmark Claude, GPT, LLaMA, Mistral, and emerging open-weight models against Snoonu's specific use cases and constraints.
• Identify and prototype the next high-leverage AI capability the team should build — bring experiments from idea to validated proof-of-concept with clear go/no-go criteria.
• Produce high-quality technical documentation: architecture decision records, experimental results, and prompt engineering playbooks for team-wide use.

• Bachelor's or Master's degree in Computer Science, AI, Software Engineering, or a related field.

• 5–8 years of hands-on software engineering experience, with at least 3 years focused on LLM-based systems, conversational AI, or agentic architectures.
• Demonstrated track record of owning and shipping production AI systems end-to-end — not just models, but the full stack from API to monitoring. Portfolio, GitHub, or detailed case studies required.
• Prior experience in a senior IC or tech lead role: setting technical direction, conducting design reviews, and mentoring engineers.
• Strong Python and backend development skills (FastAPI / Flask preferred); ability to write clean, production-grade, maintainable code.
• Research-driven mindset — obsessed with what's next in AI; able to translate frontier research into production value quickly.
• Extreme ownership: you define the problem, architect the solution, ship it, and hold yourself accountable for outcomes — without waiting to be told.
• Strong business context awareness — you think about ROI, operational impact, and user outcomes, not just technical elegance.
• Senior communicator: can explain complex agent design trade-offs to non-engineers, write compelling technical proposals, and influence direction through clarity of thought.
• Thrives in ambiguity — can operate effectively in fast-paced R&D environments where the problem definition evolves alongside the solution.
• Natural multiplier: makes the engineers around them better through code reviews, design feedback, and knowledge sharing.
• Collaborative and direct — comfortable pushing back on requirements and raising risks early, not just executing orders.

• Deep experience with Anthropic Claude (claude-3 / claude-sonnet / claude-opus) via API and AWS Bedrock — prompt engineering, tool use, and multi-turn reasoning.
• Familiarity with OpenAI GPT models and open-weight models (LLaMA 3, Mistral, Phi) — fine-tuning, quantization, and local inference is a strong plus.
• Retrieval-Augmented Generation (RAG): vector databases (OpenSearch, Pinecone, pgvector), embedding models, and hybrid search.
• Agentic frameworks: LangChain / LangGraph, CrewAI, AutoGen, or AWS Bedrock Agents.
• Prompt engineering, system prompt design, evaluation (evals), and red-teaming for production safety.

• Amazon Bedrock — model invocation, Agents for Bedrock, Knowledge Bases.
• Amazon Lex v2 — intents, slots, fulfillment Lambda, conversation logs.
• Lambda, API Gateway, Step Functions, SQS/SNS, DynamoDB, S3, CloudWatch.
• IAM, VPC, Secrets Manager — security and environment best practices.
• Experience with event-driven and serverless architectures.

• Python — OOP, async, clean code; REST API design with FastAPI or Flask.
• Containerization: Docker; orchestration experience (ECS / EKS) is a plus.
• Git, CI/CD pipelines, automated testing, and prompt versioning practices.

• Experience running local LLaMA inference (Ollama, vLLM, HuggingFace Transformers).
• Exposure to voice bots, STT/TTS pipelines, or multi-modal AI.
• Knowledge of logistics, e-commerce, or delivery operations domains.
• Arabic language NLP experience (Snoonu serves Qatar).