AI Software Engineer

OpTech; Farmington Hills (MI); On-site; USD 130,000 - 190,000; Full time

Job summary

OpTech in Farmington Hills, MI seeks a Senior AI/Python Developer to design and deploy secure, scalable AI-enabled applications for wealth and asset management. You will own Python services, ML integration, and production readiness.

The role emphasizes Generative AI, prompt engineering, RAG, document processing, and enterprise data integration, with collaboration across engineering, data, DevOps, and cybersecurity teams.

Qualifications

• 8+ years of Python/AI/ML experience in engineering roles.
• Hands-on Python with modern API frameworks.
• Experience building REST APIs with FastAPI and Pydantic.
• Proficiency with AWS services including Bedrock and Textract.
• Experience deploying LLMs and Generative AI.
• Strong prompt engineering knowledge and evaluation methods.

Responsibilities

• Design, develop, test, and maintain production-grade Python AI services.
• Build and deploy Generative AI solutions using Bedrock and LLMs.
• Develop prompt engineering templates, outputs, and reusable patterns.
• Create RAG, semantic search, embeddings, and vector retrieval systems.

Skills

Python development

AI/ML engineering

Software engineering

API development

FastAPI

Pydantic

AWS Bedrock

Amazon Textract

LLMs deployment

Generative AI

Prompt engineering

AI agents

Strands Agents

RAG

Semantic search

Embeddings

Vector databases

PostgreSQL/pgvector

Docker

Automated testing

AI governance

Data protection

Enterprise integration

Tools

FastAPI

Pydantic

Docker

PostgreSQL/pgvector

Job description

We are seeking a Senior AI/Python Developer to design, develop, and support secure, scalable AI-enabled applications within a Wealth & Asset Management environment. This role is focused on Python development, Generative AI, prompt engineering, Retrieval-Augmented Generation (RAG), document intelligence, AI agents, and enterprise AI integration. The ideal candidate combines strong software engineering skills with hands-on experience building and deploying AI solutions in production environments.

Key Responsibilities

• Design, develop, test, and maintain production-grade applications and AI services using Python.
• Build and deploy Generative AI solutions leveraging Amazon Bedrock and Large Language Models (LLMs).
• Design, optimize, and evaluate prompt engineering techniques, including prompt templates, structured outputs, and reusable prompt patterns.
• Develop Retrieval-Augmented Generation (RAG), semantic search, embedding, and vector retrieval solutions.
• Build AI agents and agent-based workflows using frameworks such as Strands Agents.
• Develop reusable AI services and APIs using FastAPI, Pydantic, and related technologies.
• Integrate AI solutions with both structured and unstructured enterprise data sources.
• Develop document processing and extraction solutions using Amazon Textract where appropriate.
• Implement vector-based retrieval strategies utilizing PostgreSQL and pgvector.
• Establish safeguards for AI output quality, validation, reliability, traceability, and secure data handling.
• Optimize AI applications for performance, latency, token consumption, and cost efficiency.
• Create automated testing, evaluation, and monitoring capabilities for AI solutions.
• Collaborate closely with application development, data engineering, DevOps, QA, architecture, cybersecurity, and business stakeholders.

Required Qualifications

• 8+ years of experience in Python development, software engineering, AI/ML engineering, or related technical roles.
• Strong hands-on experience with Python and modern API development frameworks.
• Experience developing REST APIs using FastAPI and Pydantic.
• Proficiency with AWS services, including Amazon Bedrock and Amazon Textract.
• Experience integrating and deploying Large Language Models (LLMs) and Generative AI solutions.
• Strong understanding of prompt engineering, including prompt design, testing, optimization, structured outputs, and evaluation methodologies.
• Experience developing AI agents and agentic workflows, preferably with Strands Agents.
• Experience building Retrieval-Augmented Generation (RAG) solutions, semantic search capabilities, embeddings, vector databases, and PostgreSQL/pgvector.
• Experience with Docker/containerization and automated testing frameworks.
• Strong understanding of enterprise AI security, data protection, responsible AI practices, and governance frameworks.
• Experience integrating AI solutions with enterprise applications and data ecosystems.

Preferred Qualifications

• Experience supporting AI solutions in financial services, wealth management, asset management, or other regulated industries.
• Experience with AI observability, evaluation frameworks, model monitoring, and LLMOps practices.
• Knowledge of cloud-native architectures, CI/CD pipelines, and DevOps methodologies.
• Experience designing scalable, highly available enterprise applications.

What We're Looking For

• Strong problem-solving and analytical skills.
• Ability to communicate complex AI concepts to technical and non-technical audiences.
• Experience working in cross-functional Agile development teams.
• Passion for emerging AI technologies and continuous learning.

This is an excellent opportunity for a senior-level engineer who enjoys building enterprise-grade AI solutions and shaping the future of intelligent applications.