AI Engineer

NevkaSystems; United States; Remote; USD 120,000 - 180,000; Full time

Benefits offered by this job

Fully remote

Job summary

NevkaSystems is seeking a remote AI Engineer to craft production AI applications, including conversational agents and automated workflows. You will integrate models with business APIs and build reliable backends to serve real users.

You will design prompts, evaluate model outputs, and optimize latency and costs while ensuring data safety. The role favors collaboration with cross-functional teams in a fully distributed setup.

Qualifications

• Experience building applications with large language models and external APIs.
• Strong Python or TypeScript skills for backend services.
• Understanding of tool calling, RAG and embeddings.
• Experience evaluating model responses with realistic cases.
• Knowledge of databases, authentication, Git, testing and deployment.
• Ability to explain engineering trade-offs and collaborate in a remote team.

Responsibilities

• Develop and ship AI features, including conversational and voice experiences and workflow automation.
• Connect agents to business APIs and tools with proper permissions, validation and human handoffs.
• Build retrieval pipelines for document ingestion, search and grounded responses.
• Design prompts and evaluation setups for task completion, accuracy and failure handling.
• Measure latency, streaming, reliability and cost with controlled experiments.
• Add logging, tests and safeguards for data privacy and prompt safety.
• Collaborate with product and design to turn prototypes into maintainable services.

Skills

LLM applications

Python

TypeScript

Backend services

Tool calling

Retrieval-augmented generation

Embeddings

Model evaluation

Databases

Git / DevOps

Job description

Role overview

Build production AI applications such as conversational agents, knowledge assistants and automated workflows. The role spans model integration, backend engineering and evaluation, with a focus on making features reliable, secure, responsive and useful beyond an initial prototype.

Responsibilities

• Develop and ship AI features, including conversational and voice experiences and workflow automation.
• Connect agents to business APIs and tools with appropriate permissions, validation and human handoffs.
• Build retrieval pipelines for document ingestion, search and responses grounded in source material.
• Design prompts, conversation flows and realistic evaluations for task completion, accuracy and failure handling.
• Measure and improve latency, streaming, reliability and operating cost through controlled experiments.
• Add logging, tests and safeguards for sensitive data, prompt injection and unintended tool use.
• Work with product, design and engineering colleagues to turn prototypes into maintainable services.

Requirements

• Practical experience developing applications with large language models and external APIs.
• Strong Python or TypeScript skills and experience building backend services.
• Understanding of tool calling, structured outputs, retrieval-augmented generation and embeddings.
• Experience evaluating model responses with realistic cases and investigating inconsistent results.
• Working knowledge of databases, authentication, Git, automated testing and deployment.
• Ability to explain engineering trade-offs and collaborate clearly in a remote team.

Nice to have

• Experience with real-time voice, speech technology or multilingual agents.
• Relevant project examples or a code portfolio to share.

Benefits and work setup

• Fully remote, with applicants considered worldwide.