Skip to content
Search jobs inside your AI agent. Claude, ChatGPT, Claude Code, Codex, Gemini, Cursor and Grok
Connect

Empresa Confidencial

NewBe an early applicant

Senior AI Engineer

Posted

Summary

Senior AI Engineer who architecturally builds and scales autonomous conversational AI agents (chat and voice) in production — multi-step agent workflows, RAG pipelines, voice AI (STT/TTS), and enterprise integrations. Core stack: Python, LLM providers (OpenAI, Anthropic, Gemini, etc.), agent frameworks like LangChain/LangGraph, vector databases, and Azure/AWS/GCP cloud.


About the Role

We are looking for a hands-on Senior AI Engineer to architect, build, and scale autonomous conversational AI agents in production. Rather than creating isolated AI features, you will connect Generative AI, LLM orchestration, voice and chat interfaces, APIs, and enterprise applications into a unified, production-ready AI ecosystem.

If you have 3+ years of AI engineering experience and a track record of taking LLM applications from proof of concept to production, we want to hear from you. You will thrive here if you are comfortable working across multiple model providers, designing agentic workflows, and building reliable, secure, and observable AI services.

What You Will Do

  • Build Autonomous Agents: Design and deploy multi-step AI agents for chat and voice channels, handling tool use, routing, context/memory management, and seamless human handoffs.
  • Orchestrate Agentic Workflows: Connect agents with enterprise systems using APIs, webhooks, SDKs, databases, event buses, and integration platforms.
  • Architect an AI Ecosystem: Unify LLMs, knowledge bases, customer channels, and orchestration services into a cohesive, scalable architecture.
  • Optimize Model Performance: Evaluate and tune multiple LLMs based on accuracy, latency, cost, security, context-window needs, and tool-calling capabilities.
  • Design Orchestration Patterns: Implement routing, fallback models, structured outputs, function calling, RAG pipelines, multi-agent collaboration, and state management.
  • Engineer Voice AI Experiences: Develop real-time voice interactions featuring STT/TTS, barge-in handling, low-latency optimization, call context tracking, and telephony/contact-center integrations.
  • Drive Enterprise Integrations: Connect AI workflows with CRMs, ticketing tools, knowledge management systems, identity providers, and core databases.
  • Ship Production-Grade Code: Build robust APIs and microservices following modern engineering best practices (authentication, error handling, retries, rate limiting, logging, and automated testing).
  • Measure & Monitor: Implement evaluation frameworks and observability to track hallucinations, latency, cost, containment rates, escalation metrics, and business KPIs.
  • Enforce AI Governance: Apply responsible AI principles, data privacy, security controls, and compliance standards across all solutions.
  • Collaborate & Document: Partner with architecture, security, product, and business teams to translate requirements into scalable systems, maintaining clear technical documentation.

What You Bring (Required)

  • Experience: 3+ years of professional experience in AI, Machine Learning, Generative AI, or a closely related engineering discipline.
  • Production Track Record: Proven experience taking LLM-based applications from prototype to production or advanced pilot environments.
  • Agentic Systems: Hands-on background building autonomous/semi-autonomous AI agents, agentic workflows, or tool-using conversational systems.
  • Multi-Model Fluency: Practical experience working with multiple LLM providers (e.g., OpenAI, Anthropic, Google Gemini, Meta Llama, Mistral).
  • Software Engineering: Strong Python skills alongside hands-on experience with REST APIs, JSON, asynchronous programming, Git, testing, and modern CI/CD practices.
  • AI Frameworks: Proficiency with orchestration and agent frameworks such as LangChain, LangGraph, Semantic Kernel, AutoGen, CrewAI, or similar tools.
  • RAG & Prompting: Solid experience with RAG architectures, embeddings, vector databases, prompt engineering, structured outputs, and context management.
  • Systems Integration: Track record of connecting AI solutions with external APIs and enterprise software.
  • Cloud Proficiency: Understanding of cloud-native AI architectures and hands-on experience with Azure, AWS, or Google Cloud.
  • Communication: B2+ English proficiency, with the ability to lead technical discussions and collaborate with international stakeholders.
  • Education: Bachelor’s degree in Computer Science, Software Engineering, Data Science, AI, Electrical Engineering, or equivalent practical experience.

Nice to Have (Preferred)

  • Experience with voice AI, conversational IVR, contact-center platforms, SIP/telephony, or real-time voice agents.
  • Hands-on background with enterprise AI platforms like Azure OpenAI, Amazon Bedrock, or Google Vertex AI.
  • Familiarity with MCP (Model Context Protocol) or similar standards for connecting agents to external tools and data.
  • Experience with event-driven architectures, messaging queues, API gateways, serverless computing, and microservices.
  • Proficiency with Docker, Kubernetes, Infrastructure as Code (IaC), and cloud observability tools.
  • Knowledge of AI security practices, including prompt injection defenses, DLP, PII handling, and model governance.
  • Background building AI solutions for customer support, contact centers, IT operations, or internal enterprise automation.
  • Experience defining AI technical standards, reference architectures, or reusable internal AI platforms.


Skills

What Senior AI Engineering jobs ask for — and how much of it you have →
Apply

See also

AI Engineering jobs by country — openings, pay and top skills →