AI Engineer - Generative AI / LLM / RAG

Verdeshell Technologies; Bengaluru; Presencial; INR 1 200 000 - 2 100 000; Tempo integral

Resumo da oferta

Verdeshell Technologies in Bengaluru is seeking a software engineer to build production-grade AI applications and backend services using Python and FastAPI. You will design LLM-powered apps, implement RAG pipelines, vector-search integrations and AI agents, collaborating with clients and engineering teams to translate business needs into scalable solutions.

Ideal candidates have 3–6 years of software experience, strong Python/FastAPI skills and hands-on work with LLMs, RAG pipelines and vector

Qualificações

• 3 to 6 years of software engineering experience with AI-enabled apps.
• Strong production experience with Python and FastAPI.
• Experience building LLM applications and RAG pipelines.

Responsabilidades

• Develop production-grade AI applications and backend services using Python and FastAPI.
• Design and implement LLM-powered applications and RAG pipelines including ingestion, embeddings, retrieval and response generation.
• Build AI agents and tool-calling workflows to automate business processes.
• Integrate LLM APIs and enterprise data sources with external apps.
• Work with vector databases like Pinecone, Weaviate or pgvector.
• Evaluate retrieval relevance, grounding and overall app quality.
• Implement safeguards for hallucinations and prompt injection.
• Optimize latency, reliability and cost of model usage.
• Build REST APIs, data-processing workflows and integrations across databases.
• Write maintainable code, tests and CI/CD pipelines and participate in reviews.

Conhecimentos

Python

FastAPI

LLM apps

RAG pipelines

AI agents

Vector DBs

LangChain

LlamaIndex

React.js

Secure API

Ferramentas

Pinecone

Weaviate

pgvector

Descrição da oferta de emprego

Role & responsibilities

• Develop production-grade AI applications and backend services using Python and FastAPI.
• Design and implement LLM-powered applications and RAG pipelines, covering document ingestion, chunking, embeddings, retrieval and response generation.
• Build AI agents and tool-calling workflows to automate business processes.
• Integrate LLM APIs, enterprise data sources and external applications.
• Work with vector databases such as Pinecone, Weaviate or pgvector.
• Evaluate and improve retrieval relevance, response accuracy, grounding and overall application quality.
• Implement safeguards for hallucinations, prompt injection and sensitive-data handling.
• Optimize AI applications for latency, reliability and model usage costs.
• Build REST APIs, data-processing workflows and integrations with relational, document or graph databases.
• Write maintainable code, automated tests and evaluation datasets; participate in code reviews, CI/CD and deployment.
• Collaborate with client stakeholders and engineering teams to translate business requirements into working AI solutions.

Preferred candidate profile

• 3 to 6 years of software engineering experience, including hands-on development of AI-enabled applications.
• Strong production experience with Python and FastAPI.
• Practical experience building LLM applications, RAG pipelines and AI agents.
• Strong understanding of document chunking, embeddings, semantic search, retrieval strategies and context management.
• Experience integrating LLM APIs and implementing structured outputs, tool calling and prompt workflows.
• Hands-on experience with Pinecone, Weaviate, pgvector or similar vector-search technologies.
• Ability to evaluate AI outputs, diagnose retrieval failures and improve application accuracy.
• Understanding of secure API development, testing, logging and production monitoring.
• Familiarity with frameworks such as LangChain or LlamaIndex is preferred.
• Knowledge of React.js is an advantage.
• Comfortable working directly with clients and adapting to evolving requirements.
• Available to work onsite in Bengaluru; immediate joiners preferred.