About the Role
Senior Applied AI Engineer to build production‑grade, multimodal (audio/video/text) systems that convert broadcast and radio feeds into structured, real‑time signals and event candidates. Implement and evolve “agentic” components (sensor agents, specialist agents, decision logic) powering products like Audio Intelligence, semi‑automated broadcast‑to‑data tagging, and highlight/momentum signals.
Use technical expertise and pragmatic problem‑solving in an Agile, continuous‑improvement team. Expect a data‑driven, evidence‑based mindset with continuous experimentation and validation.
Key Responsibilities
- Build and maintain multimodal agents:
- Audio sensor agents (acoustic events, sentiment, alignment)
- Visual sensor agents (scorebug/overlay reading, basic visual cues when applicable)
- Specialist and decision logic components (structured event outputs, confidence, traceability)
- Implement streaming‑friendly pipelines: chunking, normalization, time‑sync, async execution, and robust retry/backoff for model/tool calls.
- Develop prompt‑as‑code with strict JSON contracts, schema validation, and deterministic post‑processing to reduce brittleness.
- Improve system robustness under noisy inputs:
- Design fallback behaviors (degraded modes)
- Add guardrails and confidence thresholds
- Instrument traces/metrics for latency, cost, and accuracy
- Partner with product, platform, and domain leads to translate sport rules and edge cases into validation logic and integrate outputs into downstream consumers (tagging, live feeds, analytics).
- Contribute to the evaluation workflow by adding test cases, failure mode categories, and regression checks for prompts and model routing.
- Stay up‑to‑date with emerging Gen AI technologies, tools, and best practices.
- Mentor and support other team members in data engineering principles and practices.
Qualifications
- 5–8+ years of professional software engineering experience (backend and/or ML systems).
- Strong proficiency in one or more of: Python, Java, Rust.
- Hands‑on experience building production services involving LLM or multimodal model integration (Gemini, ChatGPT, Claude).
- Comfortable with ambiguity, iterative experimentation, and evidence‑based decision‑making in an Agile environment.
- Experience with streaming data platforms like Kafka, Pulsar, Flink.
- Experience with AWS Bedrock or Google Vertex AI.
- Familiarity with version control systems (Git).
- Excellent problem‑solving skills and attention to detail.
- Ability to work independently and as part of a team.
- Strong communication skills.
Preferred Qualifications
- Experience with audio ML/speech/acoustic event detection or media pipelines (audio/video chunking, sync).
- Experience with RAG or rules/config grounding for sport‑specific logic (league configs, terminology, rulebooks).
- Familiarity with evaluation practices (golden sets, precision/recall, drift monitoring) and production observability.
- Experience operating systems where cost/latency tradeoffs matter (routing “flash vs heavy” models, caching, batching).
Travel & Working Model
Occasional travel may be required. Hybrid working models differ based on role and location.
Disability Assistance
Let us know when you apply if you need any assistance during the recruiting process due to a disability.
#J-18808-Ljbffr…