Senior AI Engineer

Koda North; United States; Remote; USD 140,000 - 230,000; Full time

Job summary

Koda North is seeking a Senior AI Engineer to design, build, and scale AI-powered software systems for production use. You will translate business problems into reliable AI applications, working on LLM-powered products, AI automation, retrieval workflows, and data pipelines.

You will address evaluation, latency, cost, security, and production risk while collaborating with product, engineering, design, QA, and operations to deliver robust, scalable AI solutions.

Qualifications

• 8+ years of professional software engineering experience.
• Experience building production systems, not only prototypes.
• Hands-on AI application development with LLMs and modern AI APIs.
• Strong Python backend and server-side development skills.
• Ability to design scalable data pipelines, retrieval workflows, and AI guardrails.

Responsibilities

• Design and build production-ready AI applications and automation workflows.
• Develop LLM-powered features using modern AI APIs and backend systems.
• Build retrieval, search, RAG, document processing, and knowledge workflows.
• Design prompts, tools, evaluation flows, and guardrails for reliable AI behavior.
• Integrate AI systems with APIs, databases, and internal tools.
• Create data pipelines for ingestion, cleaning, embedding, and retrieval.
• Evaluate model outputs, debug AI behavior, and improve system quality.
• Ensure secure handling of sensitive data and access controls.

Skills

Backend engineering (Python)

AI/ML application development

LLMs & AI APIs

Data pipelines

Security & privacy

Software architecture

Documentation and code reviews

Cross-functional collaboration

Product stakeholder communication

Production-ready systems

Tools

OpenAI API

LangChain

Pinecone

Weaviate

Chroma

pgvector

AWS Bedrock

Azure AI

Docker

CI/CD

Job description

Koda North is hiring a Senior AI Engineer to design, build, and improve practical AI-powered software systems.

This role is for an experienced engineer who can turn business problems into reliable AI applications, not just prototypes. You will work on LLM-powered products, AI automation, retrieval workflows, document intelligence, data pipelines, model integrations, evaluation systems, and production-ready backend services.

The ideal candidate has strong software engineering fundamentals, hands‑on AI application experience, and the judgment to choose the right approach when working with imperfect data, changing requirements, latency limits, cost constraints, security needs, and production risk.

Responsibilities

• Design and build production‑ready AI applications, agents, and automation workflows
• Develop LLM‑powered features using modern AI APIs, frameworks, and backend systems
• Build retrieval, search, RAG, document processing, and knowledge‑based workflows
• Design prompts, tools, evaluation flows, and guardrails for reliable AI behavior
• Integrate AI systems with APIs, databases, business platforms, and internal tools
• Build backend services that support AI features, data processing, and automation
• Improve AI system accuracy, latency, cost efficiency, reliability, and maintainability
• Create data pipelines for ingestion, cleaning, transformation, embedding, and retrieval
• Evaluate model outputs, debug AI behavior, and improve system quality over time
• Implement secure handling of sensitive data, permissions, logging, and access control
• Collaborate with product, engineering, design, QA, and operations teams
• Document AI architecture, technical decisions, system limits, and operational workflows

Qualifications

• 8+ years of professional software engineering experience
• Strong experience building production software systems, not only AI prototypes
• Hands‑on experience developing AI applications using LLMs and modern AI APIs
• Strong backend engineering skills with Python and modern server‑side development
• Experience building APIs, data pipelines, integrations, and automation workflows
• Experience with RAG, embeddings, vector databases, semantic search, or document intelligence
• Strong understanding of prompt engineering, tool use, evaluation, and AI reliability patterns
• Experience working with relational databases and structured or unstructured data
• Ability to debug complex issues across AI behavior, backend systems, data quality, and production logs
• Good understanding of security, privacy, access control, and responsible AI implementation
• Ability to evaluate tradeoffs around model choice, latency, cost, accuracy, and maintainability
• Experience with Git, code reviews, technical documentation, and team‑based engineering workflows
• Clear communication with product, technical, and non-technical stakeholders
• Strong ownership mindset from technical discovery through production release and improvement

Nice to have

• Experience in healthcare, healthtech, clinical workflows, patient‑facing systems, or compliance‑aware environments
• Experience with HIPAA‑conscious engineering, PHI handling, RBAC, audit logs, or privacy‑sensitive AI systems
• Experience with OpenAI API, Anthropic, Azure AI, AWS Bedrock, LangChain, LlamaIndex, or similar tools
• Experience with vector databases such as Pinecone, Weaviate, Chroma, pgvector, or similar systems
• Experience with fine‑tuning, model evaluation, synthetic data, or human‑in‑the‑loop review workflows
• Experience with OCR, document extraction, classification, summarization, or data enrichment workflows
• Experience with AWS, Docker, CI/CD, monitoring, observability, or cloud‑based deployments
• Experience building AI agents, workflow automation, copilots, chatbots, or decision‑support tools
• Experience with data governance, compliance‑aware architecture, or secure enterprise integrations
• Experience mentoring engineers or helping define AI engineering standards

Work hours: Full time