Job Description AI/ML Engineer (Generative AI)

Experience: 5+ years overall, with 3+ years dedicated to Generative AI/LLM projects (Mid-Level)
Location: Bangalore
Employment Type: Full-Time

Role Overview
We are looking for a mid-level AI/ML Engineer with a strong foundation in software/data engineering and substantial hands-on Generative AI experience. The ideal candidate has moved beyond foundational GenAI exposure into building and owning production-grade RAG pipelines, LLM integrations, and cloud-native AI services on Azure — someone who can work independently on moderately complex problems without requiring architectural oversight.

Key Responsibilities

- Design and build end-to-end RAG pipelines — document ingestion, chunking, embedding generation, vector indexing, retrieval, and reranking
- Develop and integrate LLM-powered applications using LangChain, LangGraph, or Semantic Kernel, including multi-step/agentic workflows
- Own prompt engineering and optimization for accuracy, consistency, and cost efficiency across use cases
- Deploy and manage AI services using Azure OpenAI Service / Azure AI Foundry, with working knowledge of AKS or containerized deployment
- Build and maintain scalable APIs (FastAPI/Flask) to expose AI capabilities to downstream applications
- Implement and troubleshoot vector search solutions (FAISS, Azure AI Search) including hybrid search and relevance tuning
- Apply MLOps/LLMOps practices — model versioning, monitoring, logging, and performance evaluation of deployed AI systems




- Collaborate directly with product, data engineering, and backend teams to translate business requirements into working AI features
- Mentor junior team members on GenAI implementation practices as needed
- Independently debug and resolve production issues related to AI service performance, latency, and retrieval accuracy

Required Skills

- 5+ years total experience in software/data engineering or ML, with 3+ years specifically in Generative AI/LLM-based development
- Demonstrated ownership of RAG architecture — not just consumption of existing pipelines
- Solid working experience with LangChain, LangGraph, or Semantic Kernel
- Hands-on experience with Azure OpenAI Service or Azure AI Foundry in a production or near-production setting
- Solid Python programming skills; comfortable with asynchronous programming and REST API design
- Practical understanding of vector databases and semantic search tuning (hybrid retrieval, reranking, RRF)
- Working knowledge of MLOps/LLMOps concepts — model monitoring, CI/CD for AI services
- Ability to work independently and take ownership of features end-to-end

Good to Have

- Exposure to observability/evaluation tools (LangSmith, LangFuse, TruLens, RAGAS)
- Experience with Docker/Kubernetes for AI service deployment
- Exposure to enterprise domains — BFSI, retail, pharma, or similar
- Familiarity with Azure Document Intelligence or intelligent document processing (IDP)

Education

- B.E./B.Tech in Computer Science, IT, or related field.

📌 Ai Ml Engineer (Bengaluru)
🏢 Visara Human Capital Services
📍 Bengaluru