Platform engineer

Responsibilities:

 

-Design and develop scalable Generative AI applications using Python frameworks such as FastAPI and Flask, exposing secure and robust APIs for AI-driven services.

-Build and implement multi-agent AI systems using LangChain and LangGraph to enable orchestration, reasoning, workflow automation, and tool integration.

-Develop and optimize Retrieval-Augmented Generation (RAG) pipelines by integrating Large Language Models (LLMs) with vector databases such as FAISS, Pinecone, and ChromaDB for context-aware AI responses.

-Integrate, fine-tune, and optimize OpenAI and open-source LLMs using prompt engineering, model optimization, and performance tuning techniques.

-Implement observability, tracing, monitoring, and evaluation frameworks using tools such as Langfuse or LangSmith to improve AI system performance, output quality, governance, and cost visibility.

-Containerize AI and microservices-based applications using Docker and deploy scalable, production-grade workloads on Kubernetes (EKS).

-Build, manage, and optimize CI/CD pipelines using tools such as GitHub Actions, Jenkins, or similar platforms to automate testing, deployment, and release management.

-Leverage AWS cloud services including EC2, ECS, EKS, Lambda, and S3 to build secure, scalable, resilient, and high-performing AI platforms.

-Implement DevSecOps best practices, including infrastructure security, secrets management, access controls, and governance standards across AI and cloud platforms.

-Collaborate with cross-functional teams including engineering, architecture, DevOps, and business stakeholders to deliver enterprise-grade AI solutions.

 

Required Skills & Expertise

-Strong programming experience in Python

-Hands-on experience with FastAPI or Flask

-Expertise in LangChain, LangGraph, and AI agent frameworks

-Strong understanding of RAG architectures and vector databases

-Experience with OpenAI APIs and open-source LLMs

-Knowledge of prompt engineering and LLM optimization

-Experience with Docker and Kubernetes (EKS)

-Strong understanding of AWS cloud services

-Experience in CI/CD automation and DevSecOps practices

-Familiarity with observability and AI monitoring tools such as Langfuse or LangSmith