Applied AI Engineer

Envision Technology Solutions; Austin (TX); On-site; USD 150,000 - 190,000; Full time

Job summary

Envision Technology Solutions is seeking a backend-focused engineer to build production AI systems and agentic workflows. You will ship scalable LLM-enabled features, collaborate on tool integrations, and optimize cloud costs while owning code from development through production.

The role emphasizes hands-on coding, debugging production issues, and deploying your own work in a fast-paced environment with Go, TypeScript, Rust, and Python across AWS/GCP/Azure.

Qualifications

• 3+ years building production backend or distributed systems
• Has shipped AI/LLM features serving real users at scale — not just prototypes or demos
• Has built AI agents, skills, tools, or MCP integrations
• Proficient for backend development in Python
• Working knowledge of Go, TypeScript, or Rust
• Deep experience with cloud providers (AWS/GCP/Azure) and cost optimization
• Hands-on with Docker and Kubernetes — build, deploy, debug, scale services

Responsibilities

• Write production-grade backend services and AI-integrated features.
• Develop agentic workflows with tool use and function calling.
• Deploy and debug services in cloud and container environments.
• Evaluate LLM outputs and manage performance, latency, and reliability.

Skills

Python

Backend development

Go

TypeScript

Rust

LLM Integration

LLM Evaluation

Agentic workflows

Streaming inference

Tools

Docker

Kubernetes

Job description

3+ years building production backend or distributed systems (pre-AI experience required)

Production AI Systems

Has shipped AI/LLM features serving real users at scale — not just prototypes or demos

Agentic Systems

Has built AI agents, skills, tools, or MCP (Model Context Protocol) integrations

Python

Proficient for backend development

Secondary Language

Working knowledge of Go, TypeScript, or Rust

Deep experience with AWS/GCP/Azure — cost optimization, compute decisions, not just deployment

Container & Orchestration

Hands-on with Docker and Kubernetes — can build, deploy, debug, and scale services themselves

LLM Integration

Understands token economics, context limits, rate limiting, structured outputs, API failure modes

LLM Evaluation

Understands how to evaluate LLM outputs and the inherent challenges (non-determinism, quality measurement, regression detection)

Not just an architect — writes code, debugs production issues, deploys their own work

Preferred / Differentiators

• 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
• Streaming inference and async agent orchestration
• Cost/latency optimization: caching, batching, prompt compression
• ML observability tools: Langfuse, Arize, Braintrust, W&B
• Retrieval systems (vector search, hybrid search) — as a tool, not the focus