AI Native Software Engineer

Project Role:AI Native Software Engineer

Role Summary:Build and deploy production-grade AI applications using LLMs, RAG pipelines, and agentic systems. Work seamlessly across backend (Python/FastAPI) and frontend (React/JavaScript) stacks to deliver end-to-end solutions.

Key Responsibilities:

• Design and develop LLM-powered backend services using Python and FastAPI.
• Build Retrieval-Augmented Generation (RAG) pipelines using vector databases for enhanced context retrieval.
• Implement agentic workflows using frameworks such as AutoGen or similar to create autonomous systems.
• 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 in cloud-native environments (AWS/Azure/GCP).
• Leverage LangChain to orchestrate prompts, tools, chains, memory, and agents for complex tasks.
• Utilize LangSmith for prompt/version tracking, LLM tracing/debugging, evaluation, and performance monitoring.
• Apply best practices in prompt engineering to maintain reusable libraries.
• Collaborate with cross-functional teams ensuring security, reliability, observability, and high-performance AI systems.

Required Technical Skills:
Backend & APIs: Strong hands-on experience with Python, FastAPI, RESTful API design/consumption, and OpenAPI/Swagger specifications.
Frontend: Working knowledge of React, JavaScript, and integrating frontend apps with backend APIs.
Generative AI & LLMs: Experience working with Large Language Models (LLMs), agentic system design patterns, RAG-based applications, embeddings, vector search, context management, and prompt engineering.
GenAI/Agentic Frameworks & Tooling (Must Have): Proficiency in LangChain (chains, tools, agents, memory) and LangSmith (prompt tracing, debugging). Experience with multi-agent orchestration frameworks like AutoGen. Familiarity with protocols like MCP/A2A.
Cloud & DevOps: Docker, Kubernetes, cloud setup/deployment knowledge (AWS/Azure/GCP), and basic CI/CD understanding.
AI Productivity Tools: GitHub Copilot, Claude/Cursor/Cline or similar IDEs.

Differentiators:Experience with Vector databases (Pinecone, FAISS, Weaviate) and Graph databases (Apache AGE, Neo4j). Knowledge of Security/AuthN/AuthZ (JWT, OAuth2), monitoring tools.

Soft Skills: Strong problem-solving/debugging abilities, independent ownership, clear communication, and high curiosity for fast-evolving AI ecosystems.