AI engineer

Donato Technologies, Inc; Vienna (VA); Remote; USD 120,000 - 180,000; Full time

Job summary

Donato Technologies Inc. is seeking an AI Engineer to build agentic AI systems and robust LLM-based workflows. The role involves designing tool-calling agents, integrating with runtimes, and ensuring safety and governance across production systems.

You will productionize LLMs, build retrieval pipelines, and create cross-functional tools for automated diagnostics and remediation while maintaining traceability and cost efficiency.

Qualifications

• 5+ years of software development in one or more languages, strong hands-on experience with large Python applications.
• Practical experience with Large Language Models (LLMs): API integration, prompt engineering, fine-tuning/adaptation, and RAG/tool-using agents (vector retrieval, function calling, secure tool execution).
• Understanding of different LLMs, both commercial and open source, and their capabilities (e.g., OpenAI, Gemini, Llama, Qwen, Claude).
• Solid grasp of applied statistics, core ML concepts, algorithms, and data structures to deliver efficient and reliable solutions.
• Strong analytical problem-solving, ownership, and urgency; ability to communicate complex ideas and collaborate across global teams with measurable business impact.

Responsibilities

• Design and implement tool-calling agents that combine retrieval, structured reasoning, and secure action execution.
• Productionize LLMs by building evaluation frameworks, retrieval pipelines, and response validation for production use.
• Integrate agents with observability, incident management, and deployment systems for automated diagnostics and post-incident summarization.
• Build validator models, guardrails, and policy checks to enforce safety, reliability, and least-privilege access.
• Optimize cost and latency through prompt engineering, caching, batching, and distributed tool calls to meet strict SLOs.

Skills

Python

LLMs API

Prompt engineering

RAG Pipelines

Tool execution

Tools

Vector retrieval

Function calling

Job description

AI Engineer

anywhere in US

work in EST time zone

Build agentic AI systems: Design and implement tool-calling agents that combine retrieval, structured reasoning, and secure action execution (function calling, change orchestration, policy enforcement). Engineer robust guardrails for safety, compliance, and least-privilege access.

Productionize LLMs: Build evaluation framework for open-source and foundational LLMs; implement retrieval pipelines, prompt synthesis, response validation, and self-correction loops tailored to production operations.

Integrate with runtime ecosystems: Connect agents to observability, incident management, and deployment systems to enable automated diagnostics, runbook execution, remediation, and post-incident summarization with full traceability.

Safety, reliability, and governance: Build validator models, adversarial prompts, and policy checks into the stack; enforce deterministic fallbacks, circuit breakers, and rollback strategies; instrument continuous evaluations for usefulness, correctness, and risk.

Scale and performance: Optimize cost and latency via prompt engineering, context management, caching, model routing, and distillation; leverage batching, streaming, and parallel tool-calls to meet stringent SLOs under real-world load.

Build a RAG pipeline: Curate domain-knowledge; build data-quality validation framework; establish feedback loops and milestone framework maintain knowledge freshness.

Raise the bar: Drive design reviews, experiment rigor, and high-quality engineering practices; mentor peers on agent architectures, evaluation methodologies, and saf deployment patterns

ESSENTIAL SKILLS

1. 5+ years of software development in one or more languages strong hands-on experience building and maintaining large-scale Python applications preferred.
2. Practical experience with Large Language Models (LLMs): API integration, prompt engineering, fine-tuning/adaptation, and building applications using RAG and tool-using agents (vector retrieval, function calling, secure tool execution).
3. Understanding of different LLMs, both commercial and open source, and their capabilities (e.g., OpenAI, Gemini, Llama, Qwen, Claude).
4. Solid grasp of applied statistics, core ML concepts, algorithms, and data structures to deliver efficient and reliable solutions.
5. Strong analytical problem-solving, ownership, and urgency; ability to communicate complex ideas simply and collaborate effectively across global teams with a focus on measurable business impact.

Donato Technologies Inc. is a trusted IT staffing, consulting, and software development partner headquartered in Dallas, Texas. We support clients across industries by understanding their unique business needs and delivering tailored technology and workforce solutions. Our focus is on connecting the right talent with the right opportunity-ensuring clients receive dependable, skilled professionals and candidates receive meaningful career growth and support. We work closely with small to mid-sized organizations to provide flexible, high-quality services that drive performance, innovation, and long-term success.