Third Horizon Strategies
Overview
Third Horizon is hiring an AI Software Engineer to build SLM/LLM interfaces and machine-learning (ML) models that let internal teams and clients query, analyze, and operationalize health care price transparency data at scale. The AI Software Engineer will work at the intersection of SLMs/LLMs, cloud data platforms, and health care pricing analytics, collaborating with data engineers and analysts to turn complex datasets into secure, usable products for payers, providers, and employers.
Duties and Responsibilities
SLM/LLM applications & retrieval
Build chat/ agent flows answer questions, using retrieval patterns (embeddings/vector search, SQL templates, APIs) in collaboration with analysts and data engineers. Design prompt chains, tool use, guardrails, and offline evaluation (gold sets, accuracy/latency/cost metrics). Integrate with internal systems: GitHub (read-only), Confluence (docs), and optional BigQuery read-only Actions.
Analytics modules & services
Develop modular services and APIs using TypeScript/Node.js and Python, integrating with SQL (BigQuery Standard SQL) datasets prepared by analysts and data engineers. Package deliverables as reusable libraries or APIs (Cloud Run/Functions) with CI/CD and tests.
Data platform engineering
Contribute to Dataform (JS) data processing pipelines in collaboration with data engineers, with attention to performance (partitioning, clustering), correctness, and maintainability. Implement QC/metadata reports: stage/shard row balance, directory match rates, code-set coverage, rate adjustments, outlier bands.
Operations & governance
Apply HIPAA-aligned controls (least privilege, auditability); avoid PHI/PII use in SLM/LLM contexts. Optimize application spend (bytes billed, slot planning, caching, INFORMATION_SCHEMA monitoring).
Evaluate and select appropriate AI frameworks, libraries, and tools for specific use cases. Ensure AI deployments follow data privacy laws and internal security policies. Collaborate with operations and data engineers to integrate AI tools into existing operations platforms to increase efficiency and automate repetitive processes such as data entry, report generation, and resource allocation.
Qualifications
Bachelor's or Master's degree in Computer Science, Data Science, Health Informatics, or related field 2+ years building data or ML-backed applications in production (internships/co-ops count if substantial). Proficiency in TypeScript/JavaScript (Node.js, API services, integrations) and Python for SLM/LLM pipelines; SQL/BigQuery familiarity a plus. Hands-on with SLM/LLM app frameworks/APIs (OpenAI/Vertex) and open-source models (Hugging Face); prompt engineering, RAG, evaluation. Solid understanding of ML/data engineering: data modeling, partitioning/clustering, orchestration, CI/CD, testing. Experience on GCP (BigQuery, Cloud Storage, Cloud Run/Functions, IAM, Secret Manager); containerization (Docker). Comfortable reading and writing API specs (OpenAPI) and implementing secure, read-only integrations. Excellent communication; ability to translate complex ideas for non-technical audiences. Strong problem-solving abilities and analytical mindset Desired Skills
Excellent communication and teamwork skills Exposure to health care coding and NPI/TIN provider directory concepts. Experience with Dataform or dbt on large analytical pipelines; SQLx/JS model patterns. Vector search exposure (pgvector, Pinecone, or BigQuery vector functions) and embedding management. Observability for data apps (structured logs, traces, metrics; BigQuery INFORMATION_SCHEMA; cost dashboards). Testing frameworks (pytest, jest) and data quality checks (Great Expectations or custom assertions). Third Horizon Stack (Working Set)
Data: BigQuery (partitioning, clustering, sqlx), Dataform (JS), Cloud Storage Services: Node/TypeScript, Python (FastAPI), Cloud Run/Functions LLM: OpenAI/Vertex APIs, LangChain/LlamaIndex (pragmatic use) CI/CD & Ops: GitHub Actions, docker, Terraform (nice to have) Collab: Jira, Confluence, GitHub, ChatGPT Teams (custom GPTs/Actions)
Third Horizon is hiring an AI Software Engineer to build SLM/LLM interfaces and machine-learning (ML) models that let internal teams and clients query, analyze, and operationalize health care price transparency data at scale. The AI Software Engineer will work at the intersection of SLMs/LLMs, cloud data platforms, and health care pricing analytics, collaborating with data engineers and analysts to turn complex datasets into secure, usable products for payers, providers, and employers.
Duties and Responsibilities
SLM/LLM applications & retrieval
Build chat/ agent flows answer questions, using retrieval patterns (embeddings/vector search, SQL templates, APIs) in collaboration with analysts and data engineers. Design prompt chains, tool use, guardrails, and offline evaluation (gold sets, accuracy/latency/cost metrics). Integrate with internal systems: GitHub (read-only), Confluence (docs), and optional BigQuery read-only Actions.
Analytics modules & services
Develop modular services and APIs using TypeScript/Node.js and Python, integrating with SQL (BigQuery Standard SQL) datasets prepared by analysts and data engineers. Package deliverables as reusable libraries or APIs (Cloud Run/Functions) with CI/CD and tests.
Data platform engineering
Contribute to Dataform (JS) data processing pipelines in collaboration with data engineers, with attention to performance (partitioning, clustering), correctness, and maintainability. Implement QC/metadata reports: stage/shard row balance, directory match rates, code-set coverage, rate adjustments, outlier bands.
Operations & governance
Apply HIPAA-aligned controls (least privilege, auditability); avoid PHI/PII use in SLM/LLM contexts. Optimize application spend (bytes billed, slot planning, caching, INFORMATION_SCHEMA monitoring).
Evaluate and select appropriate AI frameworks, libraries, and tools for specific use cases. Ensure AI deployments follow data privacy laws and internal security policies. Collaborate with operations and data engineers to integrate AI tools into existing operations platforms to increase efficiency and automate repetitive processes such as data entry, report generation, and resource allocation.
Qualifications
Bachelor's or Master's degree in Computer Science, Data Science, Health Informatics, or related field 2+ years building data or ML-backed applications in production (internships/co-ops count if substantial). Proficiency in TypeScript/JavaScript (Node.js, API services, integrations) and Python for SLM/LLM pipelines; SQL/BigQuery familiarity a plus. Hands-on with SLM/LLM app frameworks/APIs (OpenAI/Vertex) and open-source models (Hugging Face); prompt engineering, RAG, evaluation. Solid understanding of ML/data engineering: data modeling, partitioning/clustering, orchestration, CI/CD, testing. Experience on GCP (BigQuery, Cloud Storage, Cloud Run/Functions, IAM, Secret Manager); containerization (Docker). Comfortable reading and writing API specs (OpenAPI) and implementing secure, read-only integrations. Excellent communication; ability to translate complex ideas for non-technical audiences. Strong problem-solving abilities and analytical mindset Desired Skills
Excellent communication and teamwork skills Exposure to health care coding and NPI/TIN provider directory concepts. Experience with Dataform or dbt on large analytical pipelines; SQLx/JS model patterns. Vector search exposure (pgvector, Pinecone, or BigQuery vector functions) and embedding management. Observability for data apps (structured logs, traces, metrics; BigQuery INFORMATION_SCHEMA; cost dashboards). Testing frameworks (pytest, jest) and data quality checks (Great Expectations or custom assertions). Third Horizon Stack (Working Set)
Data: BigQuery (partitioning, clustering, sqlx), Dataform (JS), Cloud Storage Services: Node/TypeScript, Python (FastAPI), Cloud Run/Functions LLM: OpenAI/Vertex APIs, LangChain/LlamaIndex (pragmatic use) CI/CD & Ops: GitHub Actions, docker, Terraform (nice to have) Collab: Jira, Confluence, GitHub, ChatGPT Teams (custom GPTs/Actions)