Senior AI Engineer – Chatbot & Agentic AI

About the role

Snoonu is seeking a Senior AI Engineer to become the technical anchor of its R&D team, driving the design and delivery of production‑grade conversational AI and agentic automation solutions. You will shape the architecture, set engineering standards, and mentor junior talent while influencing the strategic direction of the AI platform.

Key responsibilities

• Own end‑to‑end architecture of the conversational AI and agentic automation platform, from LLM selection to cloud infrastructure and observability.
• Define engineering standards, design patterns, and conduct design reviews to ensure high‑quality AI systems.
• Mentor junior and mid‑level engineers, review code, and accelerate LLM engineering capabilities.
• Partner with the R&D Director to evaluate emerging technologies, build roadmaps, and present trade‑off analyses.
• Lead multi‑channel chatbot development (web, WhatsApp, app) using AWS Lex, Bedrock, API Gateway, and Claude or other LLMs.
• Architect agentic AI pipelines that encode SOPs into autonomous, reliable workflows for support, order verification, and logistics.
• Design and manage AWS infrastructure (Lambda, ECS/Fargate, SQS/SNS, DynamoDB, S3, CloudWatch, Step Functions) for scalability and cost efficiency.
• Build CI/CD pipelines for prompt versioning, model rollout, A/B testing, and automated evaluations.

Required profile

• Proven senior‑level experience designing and delivering production AI systems.
• Strong leadership skills with a track record of setting technical standards and mentoring engineers.
• Deep understanding of conversational AI challenges such as multi‑turn reasoning, context persistence, and fallback strategies.
• Ability to evaluate and integrate emerging LLM technologies and make data‑driven roadmap decisions.

Required skills

• AWS services: Lex, Bedrock, Lambda, ECS/Fargate, SQS, SNS, DynamoDB, S3, CloudWatch, Step Functions, API Gateway.
• Large Language Models (LLMs) – Claude, Bedrock Agents, LangGraph, CrewAI.
• Prompt engineering, Retrieval‑Augmented Generation (RAG), and model evaluation.
• Design and implementation of CI/CD pipelines for AI workloads.
• RESTful and event‑driven integration patterns.
• Monitoring, drift detection, and observability for AI systems.

What we offer

• Technical leadership role shaping a cutting‑edge AI platform.
• Opportunity to work with frontier LLM technologies and large‑scale AWS infrastructure.
• Mentorship responsibilities and influence over the team’s technical roadmap.