Sr. Python Developer (GenAI / LLM) | Any UST Location | Immediate Joiner

UST; Bengaluru; On-site; INR 800,000 - 1,200,000; Full time

Job summary

A technology company based in Karnataka, Bengaluru, is looking for candidates ready to develop AI-powered applications proficiently using Python, while working on Retrieval-Augmented Generation architectures and AWS services. The ideal candidate should have strong skills in building and consuming REST APIs, familiarity with Kubernetes, and a solid understanding of prompt engineering for optimizing LLM responses. This role is vital for enhancing AI capabilities in an innovative environment.

Qualifications

• Strong experience with Python (3.x).
• Hands-on experience with LangGraph.
• Solid understanding of LLMs and prompt engineering.
• Knowledge of RAG architectures.
• Experience with AWS services.
• Experience building and consuming REST APIs.
• Strong understanding of asynchronous programming in Python.
• Familiarity with vector databases.
• Working knowledge of Kubernetes.

Responsibilities

• Develop and maintain AI-powered applications using Python.
• Design and implement Retrieval-Augmented Generation architectures.
• Build multi-agent workflows using LangGraph and agentic frameworks.
• Integrate LLMs with vector databases.
• Build and consume REST APIs for integration.
• Deploy and manage AI workloads using AWS services.
• Apply prompt engineering techniques to optimize LLM responses.
• Develop scalable systems using asynchronous programming.
• Deploy containerized applications using Kubernetes.
• Monitor and optimize system performance.

Skills

Python (3.x)

LangGraph

LLMs and prompt engineering

Retrieval-Augmented Generation (RAG)

AWS services

REST APIs

Asynchronous programming

Vector databases

Kubernetes

Job description

Candidates ready to join immediately can share their details via email for quick processing.

[e-mail]

Key Responsibilities

• Develop and maintain AI-powered applications using Python (3.x).
• Design and implement Retrieval-Augmented Generation (RAG) architectures.
• Build multi-agent workflows using LangGraph and agentic frameworks.
• Integrate LLMs with vector databases such as Chroma, FAISS, or Pinecone.
• Build and consume REST APIs to integrate AI services with enterprise platforms.
• Deploy and manage AI workloads using AWS services such as Lambda, S3, DynamoDB, and CloudWatch.
• Apply prompt engineering techniques to optimize LLM responses.
• Develop scalable systems using asynchronous programming in Python.
• Deploy containerized applications using Kubernetes.
• Monitor and optimize system performance and reliability.

Required Skills & Experience

• Strong experience with Python (3.x).
• Hands‑on experience with LangGraph.
• Solid understanding of LLMs and prompt engineering.
• Knowledge of RAG (Retrieval-Augmented Generation) architectures.
• Experience with AWS services such as Lambda, S3, DynamoDB, and CloudWatch.
• Experience building and consuming REST APIs.
• Strong understanding of asynchronous programming in Python.
• Familiarity with vector databases (Chroma, FAISS, Pinecone).
• Working knowledge of Kubernetes.

Nice to Have

• Experience with LangChain.
• Exposure to agent core / agentic frameworks.