Gen AI Developer

Job Title:

Experience:

Location:

Contract Duration:

Overview

Gen AI Developer

Key Responsibilities

• Design, develop, and maintain backend systems using

  Python (Flask/FastAPI)

  .
• Build and optimize

  RESTful APIs

  with enterprise-grade features such as authentication, rate limiting, and error handling.
• Integrate

  LLMs (OpenAI, Anthropic Claude, etc.)

  into enterprise workflows with advanced

  prompt engineering

  .
• Develop and implement

  Retrieval-Augmented Generation (RAG)

  systems using

  vector embeddings

  ,

  semantic search

  , and

  retrieval techniques

  .
• Model and query

  knowledge graphs

  for enterprise data relationships.
• Create

  AI orchestration pipelines

  and

  multi-step AI workflows

  using agent frameworks.
• Manage and optimize

  databases (SQL, NoSQL, vector databases)

  for performance and scalability.
• Implement

  data pipelines (ETL)

  for XML/JSON/document parsing and processing.
• Ensure secure and scalable deployment on

  cloud platforms

  (Azure, SAP BTP, serverless, or containerized environments).
• Collaborate with cross-functional teams, perform code reviews, and maintain

  Git-based workflows

  .
• Monitor, troubleshoot, and optimize applications for

  performance and reliability

  .

Requirements

• Total Experience:

  5–10 years in software development.

• Enterprise Development:

  3+ years on large-scale, complex systems.

• Python Development:

  2+ years of hands-on backend development.

• GenAI/LLM Integration:

  1–2 years of practical experience integrating LLMs or GenAI tools.
• Strong skills in

  debugging, performance profiling, and problem-solving

  .
• Familiarity with

  enterprise-grade security

  ,

  event-driven systems

  , and

  monitoring tools

  .

Technical Skills

Backend Development:

Python (Flask, FastAPI, async programming), REST APIs, PyTorch, TensorFlow, SQL, NoSQL, vector databases, ETL pipelines, XML/JSON parsing.

AI/GenAI:

OpenAI API, Anthropic Claude API, LLM integration, prompt engineering, vector embeddings, semantic search, RAG systems, knowledge graphs, AI orchestration, multi-agent workflows.

Development Environment:

Git, code review workflows, debugging tools, VS Code, PyCharm, Cursor, performance profiling, collaborative coding.

Enterprise Technologies (Preferred):

Azure, SAP BTP, Docker, Kubernetes, serverless architecture, message queues, API security, enterprise authentication, logging, monitoring, and APM tools