AI Engineer

Job Title: AI Engineer

• Immediate Joinee
• 3 levels of interview (Hiring Manager, US team, VP)
• 3 yrs of exp and 2 yrs mandate in AI
• Hybrid Mode – Mon to Thursday (Work from Office Mandatory), Friday (WFH)
• Work Location – Noida(hybrid)

Please contact or #

Job Description

Critical member of the Product Engineering team, responsible for designing, developing, and deploying AI-powered features and agentic experiences into OC Tanner’s product portfolio.

Core Responsibilities

• Design and implement AI-powered features using large language models (LLMs) from providers including Anthropic Claude, OpenAI, and open-source alternatives
• Build agentic AI systems using frameworks such as LangChain, LangGraph, and similar orchestration tools to create intelligent, multi-step workflows
• Develop and maintain production-grade AI applications that integrate with existing product infrastructure
• Architect prompt engineering strategies and retrieval-augmented generation (RAG) systems to optimize AI responses for product-specific use cases
• Collaborate with Product Managers, UX Designers, and Engineering teams to identify opportunities for AI enhancement across the product suite
• Build and optimize vector databases and semantic search capabilities to power intelligent product features
• Implement monitoring, evaluation, and quality assurance frameworks for AI system outputs
• Design and maintain APIs and integrations between AI services and core product functionality
• Prototype and validate new AI capabilities, conducting rapid experimentation to assess feasibility and value
• Ensure responsible AI practices including output validation, bias mitigation, and user privacy protection
• Document AI system architectures, decision rationales, and implementation patterns for team knowledge sharing
• Stay current with rapidly evolving AI/ML landscape and evaluate emerging tools and techniques for product application

Technical Environment

• Work with commercial LLM APIs (Anthropic Claude, OpenAI GPT-4, etc.) and open-source models
• Utilize AI orchestration frameworks including LangChain, LangGraph, and related ecosystem tools
• Develop using Python as primary language for AI/ML workflows
• Implement vector databases (Pinecone, Chroma, Weaviate, etc.) for semantic search and retrieval
• Build RESTful APIs and microservices to expose AI functionality
• Deploy AI services using cloud infrastructure (AWS, Azure, GCP)
• Integrate with existing product databases and data pipelines
• Use version control (Git) and collaborative development workflows

Skills and Special Requirements(Mandatory)

• Strong proficiency in Python programming with focus on AI/ML libraries and frameworks
• Deep understanding of large language model capabilities, limitations, and prompt engineering techniques
• Experience building production applications with LangChain, LangGraph, or similar agentic AI frameworks
• Knowledge of vector databases and semantic search architectures
• Familiarity with API design and integration patterns
• Understanding of RAG (Retrieval-Augmented Generation) system architectures
• Ability to translate business requirements into AI-powered product features
• Experience with A/B testing and evaluation metrics for AI systems
• Strong problem-solving skills and ability to work in ambiguous, rapidly-evolving technical domains
• Excellent communication skills to explain AI capabilities and limitations to non-technical stakeholders
• Understanding of responsible AI principles including bias, fairness, and privacy considerations

Education/Experience

• Bachelor’s or Master’s degree in Computer Science, Software Engineering, Data Science, or related technical field
• 3+ years of software engineering experience with at least 2 years focused on AI and looking for production experience AI/ML applications.
• Demonstrated experience shipping AI-powered features to production environments
• Portfolio of projects showcasing LLM integration and agentic AI system development preferred
• Good in Communication skills and English

…