AI Native Software Engineer

Project Role : AI Native Software Engineer

Project Role Description : Build and ship production-ready software using AI as a core part of the engineering lifecycle. Apply AI-native practices to develop and validate solutions, maintain quality and compliance, and continuously improve how software is built and operated.

Must have skills : Python (Programming Language)

Good to have skills : Agentic Design

Minimum 3 Year(s) Of Experience Is Required

Educational Qualification : 15 years full time education

Role Summary

Build and deploy production-grade AI applications using LLMs, RAG pipelines, and agentic systems

Work across backend (Python/FastAPI) and frontend (React/JavaScript) stacks

Deploy and operate AI services in cloud-native Kubernetes environment

Leverage modern GenAI frameworks and tooling to accelerate development

Key Responsibilities

Design and develop LLM-powered backend services using Python and FastAPI

Build Retrieval-Augmented Generation (RAG) pipelines using vector databases

Implement agentic workflows using frameworks such as AutoGen or similar

Design and expose RESTful APIs following OpenAPI / REST API specifications

Integrate backend AI services with React + JavaScript frontend applications

Deploy, manage, and scale AI services on Kubernetes

Use LangChain to orchestrate prompts, tools, chains, memory, and agents

Use LangSmith for:

Prompt/version tracking

LLM tracing and debugging

Evaluation and performance monitoring

Apply prompt engineering best practices and maintain reusable prompt libraries

Collaborate with cross-functional teams to deliver end-to-end AI solutions

Ensure security, reliability, observability, and performance of AI systems

Required Technical Skills

Backend & APIs

Strong hands-on experience with:

Python

FastAPI

Experience designing and consuming RESTful APIs

Familiarity with OpenAPI / Swagger specifications

Frontend

Working knowledge of:

React

JavaScript

Experience integrating frontend applications with backend APIs

Generative AI & LLMs

Hands-on experience working with Large Language Models (LLMs)

Agentic system design patterns knowledge

Experience building RAG-based applications

Knowledge of:

Embeddings

Vector search

Context management

Practical experience with prompt engineering

GenAI/Agentic Frameworks & Tooling (Must Have)

LangChain

Chains, tools, agents, memory

LangSmith

Prompt tracing, debugging, evaluation, and monitoring

Agentic frameworks

AutoGen or similar

Experience with multi-agent orchestration, tool-calling agents, planners, and executors

Protocols like MCP / A2A

Cloud & DevOps

Experience with:

Docker

Kubernetes

Understanding of cloud setup and deployment (AWS / Azure / GCP)

Basic CI/CD knowledge is a plus

Gen AI Tools

AI productivity tools for general development:

GitHub Copilot

Claude / Cursor / Cline or similar

Good to Have/Differentiators

Working knowledge/experience with

Vector databases:

Pinecone, FAISS, Weaviate, Chroma, or equivalent

Graph databases:

Apache AGE, Neo4j etc.

Strong basics in Security/AuthN/AuthZ:

JWT, OAuth2

Working knowledge of monitoring and observability tools.

Soft Skills

Strong problem-solving and debugging skills

Ability to work independently and take ownership

Clear communication and collaboration skills

High curiosity for fast-evolving AI and GenAI ecosystems