What we offer
Translucent AI is building an agentic AI platform tailored for healthcare finance. Join a mission that aims to reduce the time finance teams spend on data wrangling by delivering reliable, 24/7 AI agents that understand the specifics of each healthcare organization. Founded in 2024 and backed by GV, NEA, FPV, and Virtue, we are already deployed by healthcare organizations managing more than $5 billion in revenue. This is a hybrid role in New York City with a path to broad impact across products and customers.
If you thrive in fast paced environments and care about production AI reliability, you will find a strong fit here. You will contribute to the core capabilities that multiple teams rely on, collaborating closely with product and design to bring meaningful features to customers quickly.
Role overview
As an AI Engineer at Translucent, you will strengthen the agentic platform at the heart of our healthcare finance product. You will work hands on across research and development and platform engineering to improve agent capabilities, standardize tool surfaces, enable cross product integration, and own the evals, context, and harness engineering that makes the system reliable in practice. You will help match the right agent architecture to each use case and transform core capabilities into reusable, end to end features that ship with product and design teams.
Responsibilities
- Standardize tool surfaces and skill contracts, defining MCP style tool, connector, and skill interfaces to enable new capabilities while keeping the platform stable as it grows
- Make the agent platform integration ready, building the connective tissue so agents, tools, context, and data compose cleanly across products and selecting the appropriate architecture per use case
- Own evals and benchmarks, building production grade evaluation harnesses, replay, and benchmarks for agentic AI and gating releases based on them; accuracy is non negotiable in healthcare finance
- Lead context and harness engineering, establishing best practices for grounding agents in customer business rules and data, and for control loops that maintain reliability
- Fine tune and evaluate models, including in house and open source options, benchmarking against frontier baselines and making build versus buy decisions on model, framework, and infra
- Turn capabilities into an ecosystem by creating reusable core components that translate across features and products and shipping them end to end with product and design
Requirements
- 3+ years of software engineering experience with meaningful production work in Python
- Direct experience shipping LLM powered or agentic systems in production, not just prototypes, with an understanding of where models fail and how to ensure reliability
- Hands on experience with at least one modern agent framework (LangGraph, Google ADK, LlamaIndex, Claude Agent SDK, or equivalent) and a clear viewpoint on what to use versus build
- Production evals and benchmarking experience, including eval harnesses and benchmarks that gate real releases
- Context engineering expertise, grounding agents through retrieval, context layers, and knowledge transfer to match outputs to a specific organization or user
- Comfort with data and retrieval layers, including SQL, BigQuery or a comparable warehouse, embeddings, and vector search
- A bias toward shipping, turning ambiguous problems into a working V1 quickly and iterating from there
Technologies
- Python
-
-
- LlamaIndex
- Claude Agent SDK
- SQL
- BigQuery
- Vertex AI
- Gemini
- Claude on Vertex
- GenKit
- MCP
Role details
- Full-Time
- Office Location: New York City, hybrid
Why Translucent
Healthcare providers drive about 2.5 trillion in medical expenditures each year and operate on tight margins. Finance teams are often buried in spreadsheets, manual data pulls, and disconnected systems, spending more time gathering data than using it to drive decisions. Translucent is changing that by building an agentic AI platform designed specifically for healthcare finance. Each finance team, department, and service line can have its own AI agents that run around the clock, understand their data, business rules, and workflows.
Founded in 2024 and backed by GV, NEA, FPV, and Virtue, we have already been deployed by healthcare organizations managing more than $5 billion in combined revenue. The product market fit is clear, and we are just getting started. If you want to work at the intersection of AI and one of the most complex, consequential industries, this is the place.
Experience level
We seek engineers who own meaningful surface area and drive work forward independently. You will provide sharp architectural judgment on build versus buy decisions under ambiguity, with a bias toward shipping a working V1 quickly and making agentic systems reliable for healthcare finance.
Compensation
Base salary: $175,000-$275,000 USD plus equity
