Abridge25 days ago
Инженер-программист, GenAI
Salary not specified
MARKET
16,167 ₽median for this role
Data Scientist · 96 jobs with disclosed pay
5,800half of the offers: 13,208–20,77743,793
The employer didn't disclose pay — compare with the market yourself.
Полная занятостьУдалёнка
Responsibilities
- 01Design and build agentic systems that turn LLMs into composable, dependable tools—leveraging retrieval, tool use, agentic reasoning, and structured outputs
- 02Collaborate with ML and infra engineers to scale and optimize agentic workflows, managing latency, context windows, and model choice
- 03Write high-quality, modular code that’s graceful under failure, flexible to change, and easy to iterate on
- 04Own major architectural decisions—how we architect workflows, define data flow, cache intermediate state, and structure generative outputs
- 05Drive rigorous evaluation: build benchmark datasets, develop automated and human-in-the-loop frameworks, design experiments to surface failure modes and edge cases, run A/B tests to inform deployment, and distill insights from clinician feedback to evaluate and guide model improvement
- 06Leverage frontier capabilities: rapidly prototype with new models and model capabilities, open-source tools, and novel prompting techniques
Requirements
- 013+ years of experience building production-grade systems
- 021–2+ years focused on LLM-powered or agentic products
- 03Deep fluency with LLM APIs, prompting strategies, and orchestration patterns
- 04Experience with retrieval systems (e.g., semantic and lexical retrieval, vector DBs, efficient kNN), function calling, tool-use, or agentic workflows
- 05Working knowledge of model evaluation, experience building diverse datasets, conducting both automated and human-in-the-loop evaluations, running A/B tests, and working with subject matter experts to guide model improvement
- 06Strong Python fundamentals—including ability to write clean code, design comprehensive test-cases, and familiarity with core language features and standard libraries
- 07Experience with async programming, performance profiling, packaging, and deployment tooling is strongly preferred
- 08Must be willing to work from our SF or NYC office at least 3x per week
What we offer
- 01Hybrid work model with expectation of coming into office minimum 3 times per week
- 02Relocation assistance available for candidates willing to move to San Francisco
- 03Offices located in San Francisco, New York, and Pittsburgh