Principal Engineer

Automation Anywhere; Bengaluru; On-site; INR 1,500,000 - 2,100,000; Full time

Job summary

Automation Anywhere seeks a Cloud Generative AI and RAG Engineer with 5–6+ years of experience to build, scale, and optimize GenAI applications. You will design production-grade RAG pipelines, write robust Python code, and deploy solutions on secure cloud platforms.

This onsite role in Bengaluru requires strong skills in Python, LangChain or Hugging Face, vector databases, and cloud infrastructure (Docker/Kubernetes).

Qualifications

• 5–6+ years of cloud engineering and AI solution development.
• Expert-level Python with asynchronous programming and API development.
• Experience with LangChain/LlamaIndex/Hugging Face and vector stores.

Responsibilities

• Design, implement, and optimize production-grade Retrieval-Augmented Generation (RAG) pipelines to improve LLM accuracy.
• Develop backend code in Python using frameworks like FastAPI or similar.
• Deploy GenAI applications on secure cloud platforms (AWS, GCP, Azure).
• Tune vector databases for fast, relevant semantic search retrieval.
• Connect application frontends and internal data systems with enterprise LLMs via secure APIs.
• Monitor LLM token usage, latency, and retrieval accuracy in production.

Skills

Python

Async programming

API development

RAG development

LangChain

LlamaIndex

HuggingFace

Vector databases

Docker

Kubernetes

Prompt engineering

Education

Bachelor’s degree in Computer Science or related field

Tools

LangChain

LlamaIndex

Hugging Face

Docker

Kubernetes

Pinecone

Milvus

Chroma

Job description

About Us

Automation Anywhere is the leader in Agentic Process Automation (APA), transforming how work gets done with AI-powered automation. Its APA system, built on the industry’s first Process Reasoning Engine (PRE) and specialized AI agents, combines process discovery, RPA, end-to-end orchestration, document processing, and analytics—all delivered with enterprise-grade security and governance. Guided by its vision to fuel the future of work, Automation Anywhere helps organizations worldwide boost productivity, accelerate growth, and unleash human potential.

Job Summary

We are seeking aCloudGenerative AI and RAG Engineer with 2–3 years of professional experience to build, scale, and optimize GenAI applications.He/Shewill focus on building robust Retrieval-Augmented Generation (RAG) pipelines, writing clean Python production code, and deploying these solutions onto securecloudinfrastructure.

Location : Bangalore(Onsite)
Experience - 5 - 6+ Years

Key Responsibilities

• GenAI & RAG Development: Design, implement, and optimize production-grade Retrieval-Augmented Generation (RAG) pipelines to improve LLM accuracy.
• Python Engineering: Write clean, modular, and highly efficient backend code using Python frameworks like FastAPI or LangChain.
• CloudArchitecture: Deploy, secure, and scale GenAI applications oncloudplatforms (AWS, GCP, or Azure).
• Vector Database Management: Manage and tune Vector Databases to ensure fast, relevant semantic search retrieval.
• API Integration: Connect application frontends and internal data systems with enterprise LLMs via secure APIs.
• System Monitoring: Track LLM token usage, response latency, and retrieval accuracy in production.

Required Skills & Qualifications

Experience: 5–6+ years of cloudengineering experience and AI solution development.

• Python Mastery: Expert-level Python skills, with a focus on asynchronous programming and API development.

GenAI Ecosystems: Hands-on experience using frameworks like LangChain, LlamaIndex, Hugging Face orany similar framework.

Vector Databases: Practical experience with databases such asVespa, Pinecone, Milvus, Chroma, or any similar database.

• CloudInfrastructure: Proven experience in deploying band managingcloudcompute (Docker, Kubernetes) and serverless services.
• Prompt Engineering: Ability to systematically design and optimize prompts for specific business use cases.

Preferred Qualifications

• Familiarity with fine-tuning open-source LLMs (e.g., Llama, Mistral).
• Experience setting up MLOps/LLMOps tracking tools (e.g., LangSmith, Weights & Biases).
• Cloudcertifications focusing on DevOps or Developer pathways.

Education

• Bachelor’s degree in Computer Science, Software Engineering, or a related technical field

All unsolicited resumes submitted to any @automationanywhere.com email address, whether submitted by an individual or by an agency, will not be eligible for an agency fee.