AI Engineer

Role Overview

We are looking for a hands-on AI Engineer to design, build, and deploy practical AI solutions within our Customer Service ecosystem. This is not a research-focused or purely model-training role. The successful candidate will work closely with Customer Service, Automation, CRM, and Platform teams to identify operational pain points and translate them into production-ready AI solutions. The role will focus on building AI Agents, LLM-powered workflows, knowledge/RAG solutions, intelligent decisioning, and AI-driven automation, while integrating AI with existing platforms such as Zendesk, CRM systems, APIs, and Automation solutions. We are looking for someone who can go beyond prototypes and independently take AI use cases

from: Business Problem -> Solution Design -> Prototype -> Integration -> Evaluation -> Production Deployment -> Continuous Improvement

Key Responsibilities

1. AI Agent & Agentic Workflow Development

• Design and develop AI Agents for Customer Service and operational use cases.

• Build agentic workflows involving reasoning, decision-making, tool calling, and multi-step task execution.

• Enable AI Agents to interact with internal systems through APIs, automation tools, and other integration mechanisms.

• Design appropriate human-in-the-loop and exception-handling mechanisms for higher-risk scenarios.

2. LLM & Applied AI Development

• Develop production-ready applications using commercial and/or open-source LLMs.

• Implement prompt engineering, structured outputs, function/tool calling, context management, and LLM orchestration.

• Design AI solutions for classification, summarization, information extraction, decision support,

response generation, and workflow automation.

• Evaluate different models and approaches based on accuracy, latency, cost, security, and business requirements.

3. Knowledge & RAG

• Design and improve RAG-based knowledge retrieval systems.

• Work with structured and unstructured Customer Service knowledge, SOPs, policies, and FAQs.

• Improve retrieval quality, grounding, citation, chunking, metadata, and knowledge accuracy.

• Develop evaluation frameworks to measure AI answer quality and identify knowledge gaps.

4. Intent & Decision Intelligence

• Develop and improve customer intent classification and routing capabilities.

• Build decision logic combining customer intent, conversation context, business rules, knowledge, and system data.

• Support intelligent routing between AI, automation, and human agents.

• Develop confidence thresholds and eligibility logic to determine when AI or automation can safely take action.

5. AI + Automation / CRM Integration

• Work closely with Automation Engineers to connect AI decision-making with workflows, APIs, and automation solutions.

• Integrate AI solutions with CRM, Zendesk, internal platforms, and other operational systems.

• Build reusable tools/functions that allow AI Agents to retrieve information or trigger approved actions.

• Support the evolution from rule-based automation toward AI-triggered and agentic automation.

6. AI Quality & Evaluation

• Build systematic evaluation frameworks for production AI solutions.

• Develop metrics and test datasets covering accuracy, hallucination, retrieval quality, intent accuracy, task completion, and business outcomes.

• Support AI-powered Quality Control (AIQC) use cases such as conversation evaluation, compliance checking, root-cause classification, and quality insights.

• Establish monitoring and feedback loops to continuously improve production AI performance.

7. End-to-End AI Project Delivery

• Proactively identify operational problems that can be solved through AI.

• Translate business requirements into technical AI solutions.

• Rapidly build PoCs, validate business value, and productionize successful solutions.

• Monitor production performance and continuously improve deployed solutions.

• Work directly with Customer Service stakeholders rather than relying solely on predefined technical requirements.

Requirements

Must Have

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

• 3+ years of relevant software engineering, AI/ML, or applied AI experience, with hands-on experience building AI applications.

• Strong Python programming skills.

• Hands-on experience working with LLM APIs and/or open-source LLMs.

• Practical experience with prompt engineering, RAG, embeddings/vector search, structured output,

function/tool calling, and LLM evaluation.

• Strong understanding of REST APIs, JSON, authentication, and system integration.

• Experience building backend services or AI applications using frameworks such as FastAPI or equivalent.

• Ability to independently take a technical solution from prototype to production.

• Strong problem-solving skills and ability to understand business processes.

• Comfortable working directly with business and operational teams.