Applied AI Senior Engineer

Nexiva • Austin, TX

3d • Onsite

About The Position

This role involves building production backend or distributed systems with a focus on AI/LLM features. The engineer will be responsible for shipping AI/LLM features serving real users at scale, building AI agents, skills, tools, or MCP integrations, and working with cloud infrastructure and container orchestration. A key aspect of the role is understanding and integrating LLMs, including token economics, context limits, and API failure modes, as well as evaluating LLM outputs and their inherent challenges. This is a hands-on engineering role where the individual will write code, debug production issues, and deploy their own work.

Requirements

• 3+ years building production backend or distributed systems (pre-AI experience required).
• Shipped AI/LLM features serving real users at scale.
• Built AI agents, skills, tools, or MCP integrations.
• Proficient in Python for backend development.
• Working knowledge of Go, TypeScript, or Rust.
• Deep experience with AWS/GCP/Azure, including cost optimization and compute decisions.
• Hands-on experience with Docker and Kubernetes.
• Understanding of LLM integration concepts (token economics, context limits, rate limiting, structured outputs, API failure modes).
• Understanding of LLM evaluation methods and challenges.
• Hands-on engineering experience, including writing code, debugging, and deploying.

Nice To Haves

• Built multi-step agentic workflows with tool use and function calling.
• Experience with agent orchestration frameworks (LangGraph, CrewAI, Claude Agent SDK, Google ADK, OpenAI ADK).
• Built guardrails, fallbacks, or graceful degradation for AI systems.
• Experience with streaming inference and async agent orchestration.
• Experience with cost/latency optimization techniques (caching, batching, prompt compression).
• Experience with ML observability tools (Langfuse, Arize, Braintrust, W&B).
• Experience with retrieval systems (vector search, hybrid search) as a tool.

Responsibilities

• Build production backend or distributed systems.
• Ship AI/LLM features serving real users at scale.
• Build AI agents, skills, tools, or MCP integrations.
• Work with cloud infrastructure (AWS/GCP/Azure), focusing on cost optimization and compute decisions.
• Deploy, debug, and scale services using Docker and Kubernetes.
• Integrate LLMs, understanding token economics, context limits, rate limiting, structured outputs, and API failure modes.
• Evaluate LLM outputs and address challenges like non-determinism and quality measurement.
• Write code, debug production issues, and deploy own work.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed