Remote opportunity at
ApplaudoSenior AI Engineer (LLMs & Agentic AI)
Applaudo is hiring a Senior AI Engineer to build and operate production-grade large language model applications and agentic AI systems. The company calls itself AI-native and…
Career Tools
About This Role
Applaudo is hiring a Senior AI Engineer to build and operate production-grade large language model applications and agentic AI systems. The company calls itself AI-native and combines design, development, cloud, data and AI expertise to ship AI-powered products. The role is full-time and remote. The engineer designs, builds and refines the AI behind conversational products and automated workflows. Much of the work is classifying user intent, routing requests, calling the…
Job Description
Applaudo is hiring a Senior AI Engineer to build and operate production-grade large language model applications and agentic AI systems. The company calls itself AI-native and combines design, development, cloud, data and AI expertise to ship AI-powered products. The role is full-time and remote.
The engineer designs, builds and refines the AI behind conversational products and automated workflows. Much of the work is classifying user intent, routing requests, calling the correct APIs and data sources, and merging results from multiple sources. The engineer also builds and looks after MCP servers, the tool definitions they expose and how context is handled, supports the backend of the chat and MCP interface, and connects hosted models from Anthropic and OpenAI to live systems.
The post suits someone who makes production design calls with little supervision on a small team and can justify them to engineering leaders. The engineer works day to day alongside engineers and AI experts, joins architecture conversations, and keeps raising system quality through experiments and sound engineering habits. Using SQL to examine what models receive and return, for testing and monitoring, is part of the job.
Applicants need senior-level experience building AI applications in Python. A related degree is desired, though equivalent professional experience is accepted. The candidate must personally have built an MCP server, not merely used one, and should have handled prompt versioning, fallback plans and work on cost and latency. Being able to walk through their own technical work in depth under extended questioning, separating what they built from what they helped with or merely observed, is required, as is English fluent enough for a technical interview.
Responsibilities
- Develop and upkeep MCP servers, the definitions of available tools, and how context is handled.
- Build intent evaluation, classification and routing that sends requests to the right APIs and data sources and combines their outputs.
- Bring Anthropic and OpenAI models live inside production systems.
- Oversee prompt versioning, fallback plans and LLM performance tuning.
- Build and run evaluation frameworks that measure model quality and live performance.
- Use SQL to examine what models receive and return, for testing and monitoring.
- Help the chat and MCP interface function on the backend.
- Deliver production AI features alongside software engineers and AI specialists.
- Contribute to architecture discussions and the shape of the AI platform.
- Keep enhancing AI systems through experiments, optimization and good engineering practice.
Requirements
- Proficient in Python and disciplined software engineering habits.
- Capable with SQL against cloud data warehouses.
- Has shipped production LLM and agent-based applications.
- Familiar with tool calling, MCP servers, context control and multi-step orchestration.
- Has integrated hosted LLM APIs like Anthropic and OpenAI into live products.
- Skilled at prompt engineering, prompt versioning, fallback design and trimming cost and latency.
- Able to classify intent and route natural language requests.
- Has built conversational AI or systems that orchestrate multiple APIs.
- Knows LLM evaluation techniques and can work in a partly documented, existing codebase.
- Personally built an MCP server, not just consumed one.
- Can explain their own technical work in depth under extended questioning, separating what they built, contributed to and only observed.
- English adequate for a full technical interview or in-depth discussion.
- Good at teamwork, communication and solving problems.
Qualifications
- Undergraduate training in CS, software engineering, AI, data science or adjacent areas is welcome, though equivalent work experience also qualifies.
- Has deployed, tuned or evaluated open-source models through Hugging Face.
- Knows GPU acceleration and inference speedups.
- Familiar with MLOps: CI/CD, monitoring and repeatable pipelines.
- Has used vector stores in retrieval pipelines that feed LLMs (RAG-style systems).
- Applied natural language processing background.
- Has built AI products for clients.
Core Skills
Frequently Asked Questions
Answers are based only on the employer’s listing; where it doesn’t say, neither do we.
Is the role remote?
Yes, the posting lists the role as remote and full-time.
Is a salary stated?
The posting does not specify a salary.
What experience is needed?
Senior-level Python work on AI applications that run in live use, plus personal experience building an MCP server.
Is a degree required?
A degree in a related field is desired, but equivalent professional experience can be used instead.
How do I apply?
The posting does not specify an application process.
Sample Interview Questions
AI-generated questions tailored to this specific role — a preview of the full practice set.