Applied AI Engineer
Ai ml · Posted 15 days ago
You'll build the agentic platform at the core of Translucent, improving the underlying agent capabilities every team builds on rather than configuring agents for a single customer. You'll standardize the tool surfaces new capabilities plug into, make the platform integration-ready across products, and own the evals, co...
- Way of working
- Hybrid
- Location
- New York City, NY
- Pay range
- $175,000 to $300,000
- Level
- Senior
- Experience
- 5 to 10 years
- Type
- Full time
- Visa sponsorship
- Not offered for this role
- The company
- Hospitals and Health Care · 20 to 50 people
Skills that matter here
What you would be doing
- Standardize tool and skill surfaces. Define the MCP-style tool, connector, and skill contracts that let us add capabilities continuously without destabilizing the platform.
- Make the platform integration-ready. Build the connective tissue so agents, tools, context, and data compose cleanly across products, and match the right architecture to each use case.
- Own evals and benchmarks. Build production-grade eval harnesses, replay, and benchmarks, and gate every release on them.
- Lead context and harness engineering. Ground agents in each customer's business rules and data, and build the control loops that keep outputs reliable.
- Fine-tune and evaluate models. Fine-tune in-house and open-source models, benchmark against frontier baselines, and make the build-vs-buy calls.
The full description
Role Overview
You'll build the agentic platform at the core of Translucent, improving the underlying agent capabilities every team builds on rather than configuring agents for a single customer. You'll standardize the tool surfaces new capabilities plug into, make the platform integration-ready across products, and own the evals, context, and harness engineering that make it reliable enough for healthcare finance, where accuracy is non-negotiable.
If you love sweating the details of production AI, shipping fast, and seeing your work in customers' hands quickly, you'll feel at home here.
What You'll Do
- Standardize tool and skill surfaces. Define the MCP-style tool, connector, and skill contracts that let us add capabilities continuously without destabilizing the platform.
- Make the platform integration-ready. Build the connective tissue so agents, tools, context, and data compose cleanly across products, and match the right architecture to each use case.
- Own evals and benchmarks. Build production-grade eval harnesses, replay, and benchmarks, and gate every release on them.
- Lead context and harness engineering. Ground agents in each customer's business rules and data, and build the control loops that keep outputs reliable.
- Fine-tune and evaluate models. Fine-tune in-house and open-source models, benchmark against frontier baselines, and make the build-vs-buy calls.
Interested in this one?
There is no apply button here on purpose. Tell us about yourself, we book a short call, and if this role fits we walk you through the company and ask before anything is sent. Always free for you.
Tell us about you