Sr. Applied AI/ML Scientist (B2B)

sproutsocial; United States; Remote; USD 121,000 - 181,000; Full time

Benefits offered by this job

Lunch stipend

International travel opportunities

Job summary

Sprout Social is hiring a Senior AI Engineer to lead the design and delivery of production AI features transforming dynamic news and media signals into actionable intelligence. You will shape architecture and mentor other engineers while focusing on accuracy, reliability, and customer-facing reporting.

The role spans background agents, interactive assistants, content enrichment, and retrieval, with emphasis on latency, cost, and safety controls.

Qualifications

• Bachelor’s degree in a relevant field (CS/AI/data science) required.
• 6+ years building and operating production software, 2+ years with LLM-powered features.
• Strong Python backend engineering skills and experience with LLM APIs and prompts.

Responsibilities

• Lead design and delivery of production AI features for dynamic news/content.
• Deliver structured LLM-generated insights for reporting and alerts.
• Define tool use patterns, prompts, and output schemas; ensure quality and latency controls.
• Choose among retrieval, agents, fine-tuning, and traditional NLP approaches.
• Mentor engineers and participate in reviews with Product and UX teams.

Skills

Backend engineering

Python

LLM APIs

Vector databases

System design

Education

Bachelor’s degree in CS/AI/Data Science

Tools

Vector databases

Cloud platforms

Orchestration frameworks

Job description

Role overview

Lead the design and delivery of production AI features that turn fast-changing news and media signals into useful intelligence. The work spans background agents, interactive assistants, content enrichment, and retrieval, with a strong focus on accuracy, reliability, and customer-facing reporting. This is a senior technical role that shapes architecture and supports the growth of other practitioners.

Responsibilities

• Build and operate background and interactive agent workflows that monitor, enrich, summarize, and answer questions about large, continuously changing content collections.
• Deliver structured LLM-generated insights for reporting, alerts, and briefings.
• Set patterns for tool use, function calling, multi-step reasoning, prompts, and output schemas.
• Choose appropriately among retrieval, agents, fine-tuning, smaller models, and conventional NLP approaches.
• Establish evaluation practices, factual grounding and safety controls, and monitoring for quality, latency, cost, and model drift.
• Improve embedding and semantic search systems, and partner with Product and UX to ship features; lead design reviews, code reviews, and mentorship.

Requirements

• At least 6 years building and operating production software, including 2 or more years shipping LLM-powered features.
• Strong backend engineering skills and experience using Python or similar languages.
• Experience with LLM APIs, embeddings, similarity search, prompt design, structured outputs, and evaluation; familiarity with vector databases and LLM operations tools is also sought.
• Track record of owning production systems end to end and making architectural trade-offs involving quality, latency, and cost.
• Experience working with product and design partners, leading technical reviews, or mentoring engineers.
• Bachelor’s degree in a relevant field, such as computer science, AI, machine learning, or data science.

Nice to have

• Experience with orchestration frameworks, tool-calling or MCP-compatible systems, agentic workflows, semantic retrieval, cloud platforms, large-scale text or media analytics, or startup environments.

Benefits and work setup

The role may be based in Kraków or performed remotely within Poland.

• Office-based team members receive a daily lunch stipend
• International travel to a U.S. headquarters for team meetups may be available

Compensation and benefits depend on location and are subject to the employer’s stated policies.