Senior Python Engineer (Agentic AI)

Ambush; Porto Alegre; In loco; BRL 180.000 - 320.000; Tempo pieno

Descrizione del lavoro

Ambush is a people first company building advanced AI-powered products. We seek a backend engineer to create Python services that orchestrate multiple LLM agents, enabling seamless agent-to-agent communication and streaming APIs.

You will integrate LLM platforms like Bedrock, Anthropic, and Azure OpenAI, implement mTLS, and ensure observability with OpenTelemetry across distributed environments. Fluency in English required.

Competenze

• Proficient in Python with hands-on experience building distributed services.
• Experience with A2A protocol and multi-agent delegation is essential.
• Solid asyncio knowledge: async generators, queues, and task cancellation.
• Experience building streaming APIs delivering incremental results.
• Familiarity with LLM platforms (Bedrock/Anthropic, Azure OpenAI) and tool calling.

Mansioni

• Build and maintain Python services orchestrating LLM agents across multiple components.
• Implement agent-to-agent communication and deployment pipelines.
• Develop streaming APIs delivering results incrementally to users.
• Integrate LLMs via AWS Bedrock/Anthropic and Azure OpenAI.
• Ensure observability with OpenTelemetry and tracing tools.

Conoscenze

Python

A2A protocol

Asyncio

Streaming APIs

LangGraph

Pydantic AI

Jinja2

LLM integration

OpenTelemetry

GitHub Actions

English communication

Strumenti

Docker

Kubernetes

Datadog

Splunk

OpenTelemetry

Arize Phoenix

Kubectl

Descrizione del lavoro

Ambush is a people first company where talented, thoughtful individuals come together to build meaningful products and lasting partnerships. We believe the best work happens when people feel supported, trusted and empowered to bring their full abilities to the table.

Since 2015, because of our people first and long term mindset, we have grown into a partner relied on by some of the best companies in the world. We combine strong engineering, design and strategy with a growing strength in AI to help our clients see what is next and achieve bigger outcomes.

At the heart of everything we do is our team. We collaborate, take risks, lift each other up and take pride in doing work the right way, not settling for a quick makeshift solution. If you join Ambush, you join a group of people who want you to succeed and who show up for each other every day.

We believe in and expect real teamwork, a constant drive to be better, and delivering meaningful long term outcomes that we can be proud of together.

Responsibilities

• Build and maintain Python services that orchestrate LLM agents, including routing and delegation across multiple agents
• Implement agent-to-agent communication using the A2A protocol and agent cards
• Develop streaming APIs that deliver results to users incrementally
• Integrate LLMs through platforms such as AWS Bedrock/Anthropic and Azure OpenAI, using tool calling and prompt templates
• Instrument the application with observability and LLM tracing, and troubleshoot issues in distributed environments
• Package and deploy services in containers and Kubernetes clusters
• Secure service-to-service communication (mTLS) and manage the certificate lifecycle
• Contribute to CI/CD pipelines and version control best practices

What we'd like to see in a candidate:

• Strong Python skills
• Proven hands-on experience with the A2A protocol and multi-agent delegation (essential for this role)
• Solid experience with asyncio: async generators, queues, concurrent producers, and task cancellation
• Experience building streaming APIs that return results incrementally
• Agentic frameworks such as Pydantic AI, LangGraph, or comparable tools
• Tool calling, agent routing, and prompt templating with Jinja2
• LLM API integration (Bedrock/Anthropic, Azure OpenAI, or comparable platforms)
• Observability with OpenTelemetry and LLM tracing tools (Arize Phoenix or comparable)
• Log debugging across multiple pods (Splunk, Datadog, or similar)
• Docker (multi-stage builds, private registries, devcontainers)
• Kubernetes: deployments, services, ingress, probes, kubectl, and k9s
• mTLS as a client and certificate lifecycle management
• Git and GitHub Actions
• Excellent communication skills, and a great level of English

Nice to haves:

• Experience with Software Lifecycle (SLC) documentation, especially in regulated environments
• Background in pharmaceutical, healthcare, or life sciences projects