Senior Applied AI Engineer

Signify Technology; United States; On-site; USD 120,000 - 210,000; Full time

Job summary

Signify Technology is seeking a Senior Applied AI Engineer to design, build and deploy production-grade AI products and intelligent workflows. You will operate at the intersection of software engineering, ML and product development, translating generative AI capabilities into reliable customer-focused solutions.

This applied engineering role moves AI capabilities from experimentation to secure, scalable production systems with measurable impact.

Qualifications

• Five or more years of professional software-engineering experience.
• Commercial experience building and deploying AI or machine-learning products.
• At least one to three years of hands-on generative AI or LLM experience.
• Strong proficiency in Python and modern backend development.
• Experience building production applications using large language models.
• Practical knowledge of prompt and context engineering.
• Experience with agentic workflows, function calling and tool use.
• Strong understanding of RAG, embeddings, semantic search and vector databases.
• Experience with frameworks such as LangGraph, LangChain, LlamaIndex or equivalent.
• Experience using OpenAI, Anthropic, Gemini, Bedrock or open-source models.
• Experience creating evaluation, testing and monitoring processes for LLM applications.
• Familiarity with AWS, Azure or Google Cloud.
• Experience with APIs, Docker, CI/CD and distributed systems.
• Strong communication and cross-functional problem-solving skills.
• Evidence of independently delivering products from concept to production.
• Kubernetes and production infrastructure
• Pinecone, Weaviate, pgvector, Elasticsearch or OpenSearch
• LangSmith, Langfuse, MLflow or similar observability tools
• Model fine-tuning and open-source model deployment.
• Multi-agent architectures and Model Context Protocol integrations.
• AI security, governance and responsible-AI practices.
• Experience working with sensitive or regulated data.
• Previous start-up or customer-facing engineering experience.

Responsibilities

• Design and build LLM-powered applications, AI agents and workflow-automation solutions
• Develop agentic systems capable of reasoning, retrieving context, calling tools and completing multi-step tasks
• Build and optimise Retrieval-Augmented Generation pipelines, including ingestion, chunking, embeddings, retrieval and reranking
• Integrate models from providers such as OpenAI, Anthropic, Google and AWS
• Evaluate different models and architectures based on accuracy, latency, reliability and cost
• Develop evaluation frameworks to measure model and agent performance
• Implement guardrails, structured outputs, fallback handling and human-in-the-loop processes
• Build production-quality Python services and APIs around AI functionality
• Deploy and operate AI applications within cloud environments
• Monitor quality, hallucinations, latency, token usage, model drift and production failures
• Partner with product managers, designers, data teams and business stakeholders
• Translate ambiguous business requirements into practical technical solutions
• Contribute to architectural decisions and establish AI-engineering standards
• Mentor engineers and provide technical guidance across AI initiatives

Skills

Python

Backend development

LLMs / Generative AI

Prompt engineering

Agentic workflows

RAG & embeddings

Distributed systems

CI/CD

Docker

Kubernetes

Cloud platforms

Communication

Tools

LangGraph

LangChain

LlamaIndex

Pinecone

Weaviate

pgvector

Elasticsearch

OpenSearch

LangSmith

Langfuse

MLflow

OpenAI

Anthropic

Gemini

Bedrock

AWS

Azure

Google Cloud

Job description

We are looking for a Senior Applied AI Engineer to design, build and deploy production-grade AI products and intelligent workflows.

You will work at the intersection of software engineering, machine learning and product development, translating emerging generative AI capabilities into reliable solutions that solve genuine customer and business problems.

This is an applied engineering position rather than a research-focused role. You will be responsible for taking AI capabilities from initial experimentation through to secure, scalable and observable production systems.

What you’ll be doing

• Design and build LLM-powered applications, AI agents and workflow-automation solutions
• Develop agentic systems capable of reasoning, retrieving context, calling tools and completing multi-step tasks
• Build and optimise Retrieval-Augmented Generation pipelines, including ingestion, chunking, embeddings, retrieval and reranking
• Integrate models from providers such as OpenAI, Anthropic, Google and AWS
• Evaluate different models and architectures based on accuracy, latency, reliability and cost
• Develop evaluation frameworks to measure model and agent performance
• Implement guardrails, structured outputs, fallback handling and human-in-the-loop processes
• Build production-quality Python services and APIs around AI functionality
• Deploy and operate AI applications within cloud environments
• Monitor quality, hallucinations, latency, token usage, model drift and production failures
• Partner with product managers, designers, data teams and business stakeholders
• Translate ambiguous business requirements into practical technical solutions
• Contribute to architectural decisions and establish AI-engineering standards
• Mentor engineers and provide technical guidance across AI initiatives

What we’re looking for

• Five or more years of professional software-engineering experience
• Commercial experience building and deploying AI or machine-learning products
• At least one to three years of hands‑on generative AI or LLM experience
• Strong proficiency in Python and modern backend development
• Experience building production applications using large language models
• Practical knowledge of prompt and context engineering
• Experience with agentic workflows, function calling and tool use
• Strong understanding of RAG, embeddings, semantic search and vector databases
• Experience with frameworks such as LangGraph, LangChain, LlamaIndex or equivalent
• Experience using OpenAI, Anthropic, Gemini, Bedrock or open-source models
• Experience creating evaluation, testing and monitoring processes for LLM applications
• Familiarity with AWS, Azure or Google Cloud
• Experience with APIs, Docker, CI/CD and distributed systems
• Strong communication and cross‑functional problem‑solving skills
• Evidence of independently delivering products from concept to production
• Kubernetes and production infrastructure
• Pinecone, Weaviate, pgvector, Elasticsearch or OpenSearch
• LangSmith, Langfuse, MLflow or similar observability tools
• Model fine‑tuning and open‑source model deployment
• Multi‑agent architectures and Model Context Protocol integrations
• AI security, governance and responsible‑AI practices
• Experience working with sensitive or regulated data
• Previous start‑up or customer‑facing engineering experience

What success looks like

Within your first six months, you will have taken ownership of one or more AI capabilities, established reliable evaluation and monitoring practices, and deployed functionality that produces measurable improvements for customers or internal teams.