Senior AI Engineer

Techstra Solutions; Pittsburgh (Allegheny County); On-site; USD 150,000 - 190,000; Full time

Job summary

Techstra Solutions in Pittsburgh is seeking senior AI/data engineering professionals to build enterprise AI applications that connect Claude-based LLMs to governed enterprise data. You will design, develop, and operationalize end-to-end AI solutions.

Lead efforts in RAG, agentic AI, and tool-calling, while ensuring security, observability, and governance across data pipelines, APIs, and business processes. Strong Python and cloud experience are essential.

Qualifications

• 8+ years in software, data or analytics engineering, with recent AI/GenAI experience.
• Hands-on experience building AI/ML applications using Anthropic Claude.
• Strong Python programming experience.
• Experience integrating commercial LLMs via APIs into production apps.
• Data engineering with Databricks, Spark, SQL, Delta Lake, ETL/ELT.
• Experience with Azure, AWS or Google Cloud.
• CI/CD and modern software engineering practices.
• Ability to take a complex AI use case from concept to production.

Responsibilities

• Design and develop enterprise AI applications with Claude and Claude APIs.
• Build LLM-powered products including AI agents, copilots, and RAG workflows.
• Develop prompting strategies for structured outputs, tool use, and agentic behavior.
• Create secure integrations to access enterprise data, APIs, and business processes.
• Implement RAG architectures across structured and unstructured data.
• Establish evaluation frameworks for quality, accuracy, reliability, and business impact.
• Set AI guardrails, observability, security, and responsible AI practices.
• Design end-to-end architectures for data ingestion to model interaction.

Skills

Python

AI/ML

GenAI

API integration

Data engineering

Databricks

Spark / PySpark

Cloud experience

Tools

Databricks

Apache Spark

PySpark

SQL

Delta Lake

Unity Catalog

CI/CD

Job description

Join Techstra Solutions in Pittsburgh to design, build, and operationalize enterprise AI applications that connect Claude-based LLMs to governed enterprise data.

Responsibilities

• Design and develop enterprise AI applications using Anthropic Claude and Claude APIs
• Build LLM-powered products including AI agents, copilots, conversational applications, RAG, document intelligence, and workflow automation
• Develop prompting strategies and patterns for structured outputs, tool use, and agentic behaviors using Claude
• Create secure integrations for Claude-based applications to interact with enterprise data, APIs, applications, and business processes
• Implement retrieval-augmented generation (RAG) architectures across structured and unstructured enterprise data
• Develop evaluation frameworks to measure quality, accuracy, reliability, and business effectiveness
• Put in place AI guardrails, observability, exception handling, security, and responsible AI practices
• Optimize AI solutions for performance, reliability, scalability, and cost
• Assess emerging AI patterns and determine where they add practical value versus unnecessary complexity
• Design and build data pipelines that support AI, analytics, and machine learning workloads
• Build scalable data solutions with Databricks, Spark, PySpark, Python, SQL, and Delta Lake
• Prepare structured and unstructured enterprise data for LLM and AI consumption
• Design ingestion, transformation, enrichment, chunking, metadata, and retrieval workflows for RAG and agentic AI
• Use Unity Catalog and governance frameworks to ensure AI uses governed, secure, and traceable data
• Integrate AI applications with lakehouse, data warehouse, API, document, and operational data sources
• Apply standards for data quality, lineage, metadata, access control, and data governance
• Define end-to-end technical architectures for enterprise AI, from data ingestion through model interaction and application delivery
• Make architecture decisions across LLMs, data platforms, retrieval technologies, APIs, orchestration frameworks, and cloud services
• Create reusable AI services, frameworks, APIs, and components to support multiple business use cases
• Establish development, testing, evaluation, deployment, and monitoring patterns for production AI systems
• Participate in architecture and code reviews and mentor engineers on AI and data engineering practices
• Partner with business, data, architecture, security, governance, and engineering teams to translate business needs into implementable AI solutions

Requirements

• 8+ years of software, data engineering, analytics engineering, or related experience, including significant recent experience building AI/ML or GenAI solutions
• Hands-on experience building applications using Anthropic Claude
• Strong experience integrating commercial LLMs via APIs into production applications
• Experience building RAG, agentic AI, tool-calling, or LLM-based enterprise applications
• Strong Python programming experience
• Significant data engineering experience with: Databricks, Apache Spark / PySpark, SQL, Delta Lake, ETL / ELT, and data pipelines/integration
• Experience designing solutions combining LLMs with enterprise data
• Understanding of embeddings, vector search, semantic retrieval, context management, and document processing
• Experience with API development and application/system integration
• Strong understanding of data governance, data quality, metadata, lineage, security, and access controls
• Experience with Azure, AWS, or Google Cloud
• Experience implementing CI/CD and modern software engineering practices
• Ability to independently take a complex AI use case from concept and architecture through production implementation

Preferred Qualifications

• Experience with Claude Code in software engineering and development workflows
• Experience with Model Context Protocol (MCP) and tool-enabled/agentic architectures
• Experience with Databricks Unity Catalog and governed enterprise data environments
• Experience building AI applications against large enterprise data estates
• Experience with vector databases/vector search, embeddings, document processing, and semantic search
• Experience modernizing traditional analytics or data platforms to support AI use cases
• Familiarity with MLflow or similar lifecycle and evaluation capabilities
• Experience with Azure DevOps, GitHub, or comparable CI/CD platforms
• Experience implementing AI governance, security, evaluation, and monitoring standards

Technology Stack

• Claude, Anthropic Claude, Claude APIs
• Python
• Databricks, Apache Spark, PySpark, SQL, Delta Lake
• Unity Catalog
• ETL / ELT
• RAG, vector search, embeddings
• CI/CD
• Azure, AWS, Google Cloud
• Lakehouse, data warehouse, MLflow