Job Title: Senior AI Engineer (Generative AI & RAG)
Location: Pune / Mohali / Hyderabad (India)
Experience: 5+ Years

Job Summary:

We are seeking a seasoned Senior AI Engineer with 5+ years of software engineering experience to own, architect, and optimize our Generative AI and Retrieval-Augmented Generation (RAG) pipelines. In this role, you won't just tinker with wrappers; you will bridge the gap between complex foundation models and production-grade enterprise data. You will design reliable, low-latency AI applications that deliver highly accurate, contextual answers.

Responsibilities:

Design end-to-end RAG systems including document chunking strategies, embedding model selection, hybrid search (semantic + BM25), and cross-encoder reranking.
Build robust AI workflows using orchestration frameworks (e.g., LangChain, LlamaIndex, LangGraph) or custom-built asynchronous Python frameworks.
Deploy and manage vector databases (e.g., Pinecone, Milvus, Weaviate, or PGVector) at enterprise scale.
Implement automated evaluation harnesses (e.g., RAGAS, TruLens)



to rigorously track context recall, faithfulness, and reduce hallucinations.
Wrap AI services in high-performance, async backend APIs (FastAPI) and collaborate with MLOps/DevOps teams to deploy them securely via cloud settings (AWS/Azure/GCP).

Qualifications

Core Experience: 5+ years of qualified software engineering experience, with at least 2+ years of hands-on experience building production-level LLM and RAG applications.
Programming: Expert-level proficiency in Python (async/await paradigms, concurrency, and performance tuning).
AI/LLM Stack: Solid familiarity with frontier models (OpenAI, Anthropic, Gemini, Llama) and fine-tuning or prompt/context engineering nuances.
Data Layer: Deep understanding of embeddings, vector spaces, semantic search, and metadata filtering.
Engineering Best Practices: Proven experience navigating non-deterministic system testing, rate-limiting, latency constraints, and cos

📌 Senior Ai Engineer Pune
🏢 Bits In Glass
📍 Pune