Principal Engineer
Automation Anywhere2 months ago
Bengaluru, IndiaStaff+
Responsibilities
- Design, implement, and optimize production-grade Retrieval-Augmented Generation pipelines.
- Write clean, modular, efficient asynchronous backend code in Python using frameworks such as FastAPI or LangChain.
- Deploy, secure, and scale GenAI applications on AWS, GCP, or Azure.
- Manage and tune vector databases for fast and relevant semantic search retrieval.
- Connect frontends and internal data systems with enterprise LLMs through secure APIs.
- Monitor LLM token usage, response latency, and retrieval accuracy in production.
- Design and optimize prompts for specific business use cases.
Requirements
- 5–6+ years of cloud engineering experience and AI solution development.
- Expert-level Python skills with asynchronous programming and API development experience.
- Hands-on experience with GenAI frameworks such as LangChain, LlamaIndex, or Hugging Face.
- Practical experience with vector databases such as Vespa, Pinecone, Milvus, or Chroma.
- Experience deploying and managing cloud compute with Docker, Kubernetes, and serverless services.
- Bachelor’s degree in Computer Science, Software Engineering, or a related technical field.
- Familiarity with fine-tuning open-source LLMs such as Llama or Mistral is preferred.
- Experience with MLOps or LLMOps tracking tools such as LangSmith or Weights & Biases is preferred.
- Cloud certifications focused on DevOps or Developer pathways are preferred.
Benefits
- The position is onsite in Bangalore.
Tech Stack
Categories