Description

Required:

• Strong proficiency in Python.
• Working knowledge of at least one additional language: Java, Go, or TypeScript.
• Hands-on experience building production REST or gRPC APIs and microservices.
• Experience with AWS or Azure cloud platforms.
• Hands-on experience with Docker and Kubernetes.
• Experience building and maintaining CI/CD pipelines.
• Experience with infrastructure-as-code tools such as Terraform, CloudFormation, or Pulumi.
• Working experience with LLM integration, prompt engineering, or AI/ML application development.
• Familiarity with LangChain, LangGraph, or similar AI orchestration frameworks.
• Strong understanding of software testing, production reliability, and operational support.

Preferred:

• Experience with event-driven architectures using Kafka or AWS EventBridge.
• Experience with vector databases and semantic search solutions.
• Knowledge of agent evaluation and testing frameworks.
• Experience with observability tools such as Datadog, Splunk, or OpenTelemetry.
• Experience developing Python services using FastAPI or Flask.
• Knowledge of asynchronous Python programming.
• Experience with Redis and application caching patterns.
• Understanding of LLM behavior, agentic workflows, tool calling, and prompt management.

Responsibilities:

• Develop and maintain agent orchestration services, tool registries, and execution runtimes.
• Build REST and gRPC APIs and microservices supporting LLM integration.
• Develop solutions for prompt management and agent lifecycle management.
• Integrate LLMs and AI/ML models into production applications.
• Implement logging, monitoring, tracing, and observability for agentic workflows.
• Write comprehensive unit, integration, and end-to-end tests to maintain platform reliability.
• Collaborate with architects on platform design and technical decisions.
• Work with machine learning engineers on model integration and deployment.
• Build and support scalable cloud-based applications using AWS or Azure.
• Contribute to CI/CD pipelines, infrastructure-as-code, and deployment automation.
• Participate in code reviews and maintain clean, testable, and well-documented code.
• Participate in on-call rotations and provide production support for the AI platform

Key Skills

Education

Any Gradute