Overview
Generative AI Engineer to design and build scalable GenAI solutions using LLMs and RAG, deploy models in cloud platforms, and optimize reliability, security, compliance, and performance.
What you'll do
- Collaborate with Data Scientists and ML and Platform Engineers to deliver business-centric GenAI solutions.
- Build LLM-powered applications using LangChain, LlamaIndex, and related GenAI frameworks.
- Implement RAG pipelines with vector databases to ground LLM responses with internal knowledge.
- Develop multimodal AI solutions and build autonomous agents where relevant.
- Drive MLOps activities including CI/CD for ML pipelines, drift detection, canary releases, and retraining schedules.
- Design prompt templates and tune prompt flows to improve reliability, relevance, and UX.
- Deploy GenAI models on AWS/GCP/Azure and implement performance observability and security/compliance guardrails.
What you'll need
- 5+ years of experience in NLP/ML/AI.
- At least 3 years hands-on experience in GenAI.
- Strong Python coding skills with frameworks like PyTorch and Hugging Face.
- Proven experience with cloud-based AI services (AWS/GCP/Azure) and APIs (OpenAI, Anthropic, Hugging Face).
- Experience with vector databases including Qdrant, pgvector, Pinecone, FAISS, Milvus, or Weaviate.
- Familiarity with prompt engineering, transformer architectures, and embedding techniques.
- Bachelor’s/master's degree in computer science, AI, or a related field.
Details
- Position based in Mumbai (onsite).
Read the full description and apply on the company’s own careers page.
