Senior AI Engineer
Why Translucent
Healthcare providers drive $2.5 trillion in medical expenditures annually — and operate on razor-thin 2–5% margins. Despite these stakes, the finance teams behind these organizations are buried in spreadsheets, manual data pulls, and disconnected systems, spending more time finding and cleaning data than actually using it to make decisions.
Translucent is changing that. We're building the agentic AI platform designed exclusively for healthcare finance— giving every finance team, department, service line their own arsenal of AI Agents that run 24/7, understand their specific data, business logic, and workflows.
Founded in 2024 and backed by GV, NEA, FPV, and Virtue, we've already been deployed by healthcare organizations managing over $5 billion in combined revenue. The product-market fit is real, the problem is massive, and we're just getting started. If you want to work at the intersection of AI and one of the most complex, consequential industries in the world — this is the place.
About the Role
We’re building healthcare’s AI financial analyst. Our agents autonomously plan multi-step workflows, select and invoke tools, retrieve context from heterogeneous data sources, execute SQL, generate visualizations, and synthesize findings. As an AI Engineer you’ll own the full lifecycle of these agentic features — from tool design and retrieval strategy through orchestration, evaluation, and production monitoring.
What You’ll Do
- Design agentic workflow graphs in LangGraph — nodes, conditional routing, state management, and error recovery for multi-step analytical tasks
- Build and maintain a library of composable agent tools (SQL executor, chart generator, file parser) with typed schemas LLMs can reliably discover and call
- Design retrieval pipelines that supply agents with the right context: semantic search, hybrid retrieval, re-ranking, and context-window optimization
- Own the semantic layer that maps natural language to customer BigQuery schemas, business rules, and query patterns across multi-tenant datasets
- Author, version, and evaluate prompts for Gemini models — structured outputs, tool-calling specs, and guardrails
- Build evaluation frameworks: unit tests for tools, LLM-as-judge scoring, golden-answer benchmarks, and end-to-end regression suites
- Instrument agent runs with tracing and observability to diagnose failures, measure latency, and optimize cost
What You Bring
Must Have
- Agent systems: Shipped agentic architectures — state machines, tool routing, planning loops. LangGraph, CrewAI, Autogen, or similar.
- Tool design: Built tool-calling pipelines — schemas, selection, invocation, validation, and multi-step chaining.
- Retrieval engineering: RAG pipelines, vector + keyword hybrid search, re-ranking, embedding strategies, context-window management.
- LLM engineering: Prompt design, structured output extraction, guardrails, and systematic evaluation of non-deterministic systems.
- Python: Production-grade Python 3.10+ with async/await and Pydantic. This is ~80% of the work.
- SQL: Analytical SQL fluency. BigQuery or comparable columnar warehouse experience is a plus.
- Testing: pytest, mocking LLM responses, evaluation-driven development.
Bonus
- GCP services (BigQuery, Vertex AI, Cloud Storage, Cloud Run)
- Text-to-SQL or semantic layer systems
- MCP (Model Context Protocol) or agent-tool interop standards
- Vector databases (Pinecone, Weaviate, pgvector)
- Healthcare data or enterprise multi-tenant SaaS
Mindset
- Comfortable with ambiguity — agentic AI is experimental by nature
- Owner mentality — end-to-end, from design through production reliability
- Architecture thinker — enjoys refactoring monoliths into composable tools
- Customer-first — driven to solve real problems for healthcare operators
Why Translucent
We help healthcare providers make faster, smarter decisions without digging through dashboards or waiting on analyst teams. Backed by top-tier investors, our team combines deep healthcare expertise and technical excellence to reinvent how work gets done in healthcare systems.
- Competitive salary + equity at an early-stage company
- High-impact role shaping the core agentic AI platform
- Hybrid NYC with flexibility
- Collaborative team of engineers, domain experts, and forward-deployed partners
Join us in building a world where hospitals and clinics don't have to choose between financial health and patient health. Translucent automates manual data work so healthcare finance teams can focus on moving the margin—giving hospitals the financial clarity they need to thrive.
Anticipated compensation range: $200,000 - $250,000
Apply for this job
*
indicates a required field