Job description

About the Role

The GenAI/RAG Senior Engineer is a hands-on technical specialist responsible for building production-grade Generative AI solutions including Retrieval-Augmented Generation (RAG) systems, prompt engineering, agent workflows, and LLM orchestration. This role works on high-priority use cases requiring advanced GenAI capabilities, establishes engineering best practices for the team, and provides technical mentorship to junior engineers. The Senior Engineer partners with the AI Architect on solution design, implements RAG pipelines and agent systems, conducts model evaluation and optimization, and ensures solutions meet production quality, performance, and cost requirements. This role requires deep technical expertise in modern GenAI technologies and the ability to translate business requirements into working technical solutions.

• Build production-grade GenAI solutions including RAG pipelines, prompt engineering, agent workflows, and LLM orchestration

  
  

• Implement vector databases, embedding models, retrieval systems, and context management for RAG architectures

  
  

• Develop and optimize prompts, chains, and agent workflows for business use cases

  
  

• Conduct model evaluation, testing, and optimization for quality, latency, cost, and safety

  
  

• Establish GenAI engineering best practices including code standards, testing frameworks, and deployment patterns

  
  

• Integrate GenAI solutions with enterprise systems, APIs, and data sources

  
  

• Implement monitoring, logging, and observability for production GenAI systems

  
  

• Provide technical mentorship and code reviews for junior AI engineers

  
  

• Partner with Data Engineer on data pipelines and feature stores for GenAI use cases

  
  

• Capture and document reusable patterns, accelerators, and lessons learned

  
  

KPIs can include but are not limited to:

● Solution delivery: number of GenAI use cases successfully deployed to production.

• ● Quality metrics: accuracy, relevance, and safety of GenAI outputs meeting business requirements

  
  

• ●Performance optimization: latency and cost efficiency of deployed GenAI solutions

  
  

• ●Code quality: peer review ratings and technical debt metrics

  
  

Educational Qualifications: Bachelor's or Master's degree in Computer Science, Engineering, Data Science, or related technical field.

Experience: 8+ years software engineering experience with 3+ years focused on AI/ML and 1+ years on GenAI/LLMs. Hands-on experience building production RAG systems, prompt engineering, and LLM orchestration. Experience with modern GenAI platforms (OpenAI, Anthropic, Google, Azure OpenAI) and frameworks (LangChain, LlamaIndex).

Knowledge: Deep expertise in GenAI technologies including LLMs, embeddings, vector databases, RAG architectures, and agent frameworks. Strong Python programming skills. Experience with cloud platforms (AWS/Azure/GCP) and MLOps practices. Understanding of NLP, semantic search, and information retrieval.