Applied AI Engineer

Role-Applied AI Engineer

Type-Full Time

Location-Austin,TX

JJob Description – AI / Agentic Systems Backend Engineer

Role Overview

We are seeking a hands-on AI/Backend Engineer with strong experience building and operating production-grade backend or distributed systems. The ideal candidate must have practical experience shipping AI/LLM-powered features to real users at scale, building agentic systems, and independently developing, debugging, deploying, and scaling production services.

This is a highly hands-on engineering role. We are looking for a strong individual contributor who can write production code and work across backend systems, cloud infrastructure, containers, orchestration, and AI/LLM integrations.

Must-Have Requirements

Backend / Systems Experience

• 3+ years of experience building production backend or distributed systems.
• Strong pre-AI backend or systems engineering experience is required.

Production AI Systems

• Experience shipping AI/LLM-powered features serving real users at scale.
• Experience must be beyond prototypes, proof-of-concepts, or demo applications.

Agentic Systems

• Hands-on experience building AI agents, skills, tools, or MCP (Model Context Protocol) integrations.
• Experience developing systems where agents interact with tools, services, or external systems.

Python

• Strong proficiency in Python for backend development.

Secondary Programming Language

• Working knowledge of at least one of the following:
• Go
• TypeScript
• Rust

Cloud Infrastructure

• Deep hands-on experience with AWS, GCP, or Azure.
• Experience making infrastructure and compute decisions, including cost optimization, rather than only deploying applications.

Container & Orchestration

• Hands-on experience with Docker and Kubernetes.
• Ability to independently build, deploy, debug, scale, and operate services in production environments.

LLM Integration

Strong understanding of practical LLM integration challenges, including:

• Token economics
• Context limits
• Rate limiting
• Structured outputs
• API failure modes

LLM Evaluation

• Understanding of how to evaluate LLM outputs in production.
• Experience or knowledge of challenges related to:
• Non-deterministic outputs
• Quality measurement
• Regression detection

Hands-On Engineering

• Must be a hands-on engineer, not only an architect or technical strategist.
• Comfortable writing code, debugging production issues, deploying services, and owning work through production.

Preferred / Differentiators

Candidates with the following experience will be strongly preferred:

• Experience building multi-step agentic workflows involving tool use and function calling.
• Experience with agent orchestration frameworks such as:
• LangGraph
• CrewAI
• Claude Agent SDK
• Google ADK
• OpenAI ADK
• Experience building guardrails, fallbacks, or graceful degradation mechanisms for AI systems.
• Experience with streaming inference and asynchronous agent orchestration.
• Experience with cost and latency optimization, including:
• Caching
• Batching
• Prompt compression
• Experience with ML/LLM observability tools such as:
• Langfuse
• Arize
• Braintrust
• Weights & Biases (W&B)
• Experience with retrieval systems, including vector search or hybrid search, used as a supporting tool rather than the primary focus.

Ideal Candidate Profile

The ideal candidate combines strong traditional backend/distributed systems experience with proven production AI/LLM and agentic systems experience. They should be capable of independently building and operating scalable services while understanding the practical challenges of LLM reliability, evaluation, cost, latency, and production deployment.