AI Softwear Engineer

Tredence Inc.; Bengaluru; Hybride; INR 1 500 000 - 2 800 000; Plein temps

Résumé du poste

Tredence Inc. in Bengaluru is seeking a senior backend AI engineer to join our team focused on building scalable AI-powered applications.

You will design APIs with Python and FastAPI, integrate PostgreSQL, and develop RAG-led solutions using LangChain/LangGraph, OpenAI, and cloud tools. Join a fast-moving, collaborative team delivering multi-agent orchestration and advanced AI deployments.

Qualifications

• Python backend development for automation and APIs.
• PostgreSQL design, queries, and performance tuning.
• API design and scaling with FastAPI.
• Docker for containerization and deployment.
• Agentic AI frameworks (LangChain, LangGraph) for multi-agent orchestration.
• LLM API integration (OpenAI, Azure OpenAI).
• Retrieval-Augmented Generation (RAG) solutions.
• Prompt engineering to optimize LLM outputs.
• AI-powered apps, chatbots, copilots, or automation.
• Vector databases, embeddings, semantic search.
• Debugging, problem solving, and system design.
• Agile collaboration with cross-functional teams.

Connaissances

Python

PostgreSQL

FastAPI

Docker

LangChain

LangGraph

OpenAI API

Azure OpenAI

RAG

Prompt Engineering

Vector databases

Embeddings

Semantic search

Debugging

System design

Agile teamwork

Outils

FastAPI

Docker

OpenAI API

Azure OpenAI

LangChain

LangGraph

Description du poste

Required Skills & Experience

• Strong proficiency in Python for backend development, automation, and API integration.
• Hands‑on experience with PostgreSQL, including database design, query optimization, and performance tuning.
• Expertise in building scalable APIs using FastAPI.
• Experience with Docker for containerization and application deployment.
• Strong understanding of Agentic AI frameworks, including LangChain and LangGraph, with experience in multi‑agent orchestration.
• Hands‑on experience integrating and working with LLM APIs, such as OpenAI and Azure OpenAI.
• Experience designing and implementing Retrieval‑Augmented Generation (RAG) solutions.
• Strong knowledge of Prompt Engineering techniques for optimizing LLM performance and outputs.
• Experience building AI‑powered applications, chatbots, copilots, or intelligent automation solutions.
• Familiarity with vector databases, embeddings, and semantic search concepts.
• Strong debugging, problem‑solving, and system design skills.
• Ability to work in an agile environment and collaborate with cross‑functional teams.

Preferred Experience:

• 5+ years of experience in Python backend development.
• 2+ years of hands‑on experience with Generative AI, LLMs, Agentic AI, and RAG‑based applications.
• Exposure to cloud platforms such as AWS, Azure, or GCP is an added advantage.
• Experience leading small teams or mentoring junior developers is preferred.