SENIOR AI/ML FULL STACK ENGINEER

TALENT Software Services; Rochester (MN); On-site; USD 120,000 - 180,000; Full time

Job summary

TALENT Software Services in Rochester, MN seeks an experienced AI Software Engineer to design, develop, and deploy AI solutions addressing business needs. You will guide the team through full lifecycle, collaborating with product managers, designers, data scientists, and stakeholders to deliver reliable AI solutions on-prem or in the cloud.

The ideal candidate has strong Python/SQL skills, hands-on Generative AI experience, and a track record with LLMs, embeddings, and semantic search.

Qualifications

• Strong Python and SQL fundamentals with production experience.
• Hands-on Generative AI or RAG-based app development.
• Experience with LLMs, embeddings, and semantic search.
• ML/NLP model development, evaluation, and monitoring.
• Familiarity with LLM evaluation metrics (relevance, faithfulness, citations).
• Experience implementing AI safety guardrails and content moderation.
• Cloud platform experience (GCP, AWS, OCI).
• Proficiency with Vertex AI, AWS Bedrock, SageMaker, BigQuery, Snowflake, OpenSearch, Cloud Run, Docker, Airflow, Terraform, CI/CD.
• Healthcare/clinical/enterprise data experience preferred.
• Strong communication with technical and non-technical stakeholders.

Responsibilities

• Design, develop, and implement AI software solutions to address business needs.
• Assist the System Architect in the full AI solution lifecycle from design to release.
• Gather requirements from product managers, designers, data scientists, and stakeholders.
• Provide technical leadership to the software engineering team.
• Lead the team through design, development, testing, and release for on-prem or cloud.
• Improve software development processes and keep the team current with tech trends.
• Provide status reports to management and stakeholders as needed.
• Coach and guide engineers on the team.
• Build scalable AI solutions combining LLMs, retrieval, data, cloud services, and UI.
• Develop RAG pipelines, ingestion workflows, semantic search, embeddings, and monitoring.
• Collaborate closely with product owners and stakeholders to deliver reliable AI solutions.

Skills

Python

SQL

Generative AI

LLMs

Prompt engineering

Embeddings

Semantic search

Citations

ML/NLP

Evaluation

AI safety guardrails

GCP

AWS

OCI

Vertex AI

AWS Bedrock

SageMaker

BigQuery

Snowflake

OpenSearch

Cloud Run

Docker

Airflow

Terraform

CI/CD pipelines

Healthcare data

Communication

Education

Bachelor's degree in Computer Science, Data Science, Engineering, Biomedical Engineering, Statistics, Applied Mathematics

Master's degree or higher preferred in Data Science, Computer Science, Biomedical Engineering, AI, ML, Engineering

Certifications or coursework in Generative AI, ML, Cloud AI platforms, Data Science, or MLOps preferred

Job description

• Design, develop, and implement AI software solutions to address business needs.
• Assist the System Architect in the complete AI solution development and release lifecycle.
• Communicate with product managers, designers, data scientists, and other internal and external stakeholders to gather requirements.
• Help provide technical leadership to the software engineering team.
• Take direction from the System Architect and help lead the team through the software design, development, testing, and release cycle to deliver and support the final AI solutions on-prem or on cloud.
• Actively seek ways to improve the software development process and keep the team up to date on the latest software technologies and processes.
• Provide clear and accurate status reports to management and stakeholders as needed.
• Guide and coach members of the software engineering team.
• Responsible for designing and developing scalable AI solutions that combine large language models, retrieval systems, structured and unstructured data, cloud services, and user-facing applications.
• Build RAG pipelines, document ingestion workflows, semantic search, embeddings, prompt engineering, evaluation frameworks, guardrails, APIs, and production monitoring.
• Collaborate closely with product owners, clinical or business stakeholders, and technical teams to gather requirements, communicate tradeoffs, and deliver reliable, measurable AI solutions.

Job Summary:

• Design, develop, and implement AI software solutions to address business needs.
• Assist the System Architect in the complete AI solution development and release lifecycle.
• Communicate with product managers, designers, data scientists, and other internal and external stakeholders to gather requirements.
• Help provide technical leadership to the software engineering team.
• Take direction from the System Architect and help lead the team through the software design, development, testing, and release cycle to deliver and support the final AI solutions on-prem or on cloud.
• Actively seek ways to improve the software development process and keep the team up to date on the latest software technologies and processes.
• Provide clear and accurate status reports to management and stakeholders as needed.
• Guide and coach members of the software engineering team.
• Responsible for designing and developing scalable AI solutions that combine large language models, retrieval systems, structured and unstructured data, cloud services, and user-facing applications.
• Build RAG pipelines, document ingestion workflows, semantic search, embeddings, prompt engineering, evaluation frameworks, guardrails, APIs, and production monitoring.
• Collaborate closely with product owners, clinical or business stakeholders, and technical teams to gather requirements, communicate tradeoffs, and deliver reliable, measurable AI solutions.

Required Skills:

• Strong Python programming and SQL experience.
• Hands-on experience building Generative AI or RAG-based applications.
• Experience with LLMs, prompt engineering, embeddings, semantic search, query expansion, and citations.
• Experience with ML/NLP model development, evaluation, and performance monitoring.
• Familiarity with LLM evaluation metrics such as answer relevance, context relevance, faithfulness, hallucination reduction, and citation accuracy.
• Experience implementing AI safety guardrails, content moderation, blocked topics, or escalation logic.
• Experience with cloud platforms such as GCP, AWS, or OCI.
• Experience with tools such as Vertex AI, AWS Bedrock, SageMaker, BigQuery, Snowflake, OpenSearch, Cloud Run, Docker, Airflow, Terraform, or CI/CD pipelines.
• Experience working with healthcare, claims, clinical, regulatory, life sciences, or enterprise data preferred.
• Strong communication skills and ability to work with both technical and non-technical stakeholders.

Education Requirements:

• Bachelor's degree required in Computer Science, Data Science, Engineering, Biomedical Engineering, Statistics, Applied Mathematics, or a related technical field.
• Master's degree or higher preferred in Data Science, Computer Science, Biomedical Engineering, Artificial Intelligence, Machine Learning, Engineering, or a related field.
• Relevant certifications or coursework in Generative AI, Machine Learning, Cloud AI platforms, Data Science, or MLOps are preferred.