About this role.
Sporty is seeking a Senior AI Engineer to build and improve production AI capabilities across existing products in a remote-first environment. The role centers on LLM integrations, conversational and voice AI, RAG pipelines, agent workflows, and connections to internal and third-party services. The engineer will own reliability, latency, performance, operational cost, monitoring, troubleshooting, and resolution of AI-related production issues. Success requires strong Python and distributed-systems expertise, independent problem solving, and close collaboration with AI scientists, product managers, and engineering teams.
Role DNA
A quick view of the complexity, pace, ownership and collaboration implied by the job description.
Job Complexity
5/5Pace & Pressure
4/5Autonomy Level
5/5Communication Load
4/5Salary analysis
Estimated compensation compared with the broader US market for similar roles.
Core skills
Skills and capabilities most closely associated with this opportunity.
Cover letter sample
Dear Hiring Team,
I am excited to apply for the Senior AI Engineer role at Sporty. With extensive software engineering experience and hands-on delivery of production LLM applications, I can build reliable conversational AI, voice AI, RAG pipelines, and agent workflows that create measurable product value.
I bring strong Python, distributed-systems, and AI API integration experience, with a focus on latency, reliability, observability, security, and cost optimization. I am comfortable owning complex production investigations end to end while partnering closely with product managers, AI scientists, and engineering stakeholders.
Sporty’s remote-first culture and emphasis on practical, scalable AI capabilities are especially compelling to me. I would welcome the opportunity to help strengthen and expand your AI-powered products.
Sample interview questions
I would first define the user problem, success metrics, risk boundaries, and expected traffic profile. I would select an appropriate model and orchestration design, build evaluation datasets and automated tests, implement observability for quality, latency, token use, and failures, then launch gradually with monitoring and rollback controls.
I would validate retrieval quality before changing the model by reviewing document ingestion, chunking, metadata, embedding choice, hybrid search, ranking, and context assembly. I would use a representative evaluation set to measure retrieval recall and answer faithfulness, then improve the pipeline through reranking, better source coverage, prompt constraints, and citations where appropriate.
I would trace latency across retrieval, network calls, model inference, tool execution, and post-processing to identify the dominant bottleneck. Depending on the findings, I would use caching, asynchronous execution, parallel retrieval, smaller or routed models, prompt and context reduction, batching, and clear timeout and fallback policies.
I would use structured logs, distributed traces, request correlation IDs, dashboards, and alerts to identify the scope and impact quickly. I would mitigate customer impact with rate limits, feature flags, retries, fallbacks, or rollback; then perform root-cause analysis, document findings, and add tests, monitoring, or architectural safeguards to prevent recurrence.
I communicate assumptions, tradeoffs, risks, metrics, and delivery milestones in language appropriate to each audience. For example, I translate model quality and operational constraints into user impact and business outcomes for product stakeholders, while providing engineers and AI scientists with technical design details and evaluation evidence.
About the role
We are looking for a Senior AI Engineer to develop and enhance AI-powered capabilities across our existing products. You will implement new AI features, integrate emerging AI technologies and ensure our conversational and voice AI solutions remain reliable, scalable and performant. Working closely with AI Scientists, Product Managers and engineering teams, you will bring AI improvements into production while maintaining high engineering standards.
What you’ll be doing
- Develop and enhance AI-powered features across existing products.
- Integrate and maintain LLMs and AI services within production applications.
- Implement conversational AI, AI voice and intelligent workflow capabilities.
- Build and optimize RAG pipelines and agent workflows.
- Integrate AI capabilities with internal systems and external services.
- Monitor, troubleshoot and resolve AI-related production issues from identification through root cause analysis and resolution.
- Improve application performance, reliability, latency and operational costs.
- Collaborate with Product Managers and AI Scientists to improve AI quality and user experience.
- Evaluate and adopt new AI technologies where they provide business value.
- Maintain technical documentation and contribute to architecture discussions and engineering best practices.
What you’ll bring
- 5+ years of software engineering experience.
- Experience developing production AI applications using LLM.
- Strong proficiency in Python.
- Experience integrating AI APIs such as OpenAI, Anthropic or Google Gemini.
- Experience with RAG architectures and modern AI frameworks.
- Strong understanding of software architecture and distributed systems.
- Ability to independently investigate and resolve complex production issues.
- Excellent communication and stakeholder management skills.
- Proactive mindset with strong ownership and accountability.
What’s in it for you
- Sporty is a remote first company in pursuit of sustainability
- A competitive salary + individual performance based bonuses every quarter
- 28 days paid annual leave
- Our core working hours are 10am-3pm in your local time zone with flexibility outside of this
- Referral bonuses & flash bonuses
- Top of the line equipment
- Annual company retreats to provide great internal networking opportunities
Interview Process
- Remote video screening with our Talent Acquisition Team
- Online home assignment
- Remote video interview with Team Members (3×45 Mins)
If you’re interested, we encourage you to apply! Every application is reviewed by a member of our team (AI is not used in our recruitment process), and we aim to respond within 48 hours.
Annual salary information is not provided for this position. Explore salary ranges for similar roles in our Salary Directory ›
This job listing has been manually reviewed by the Jobicy Trust & Safety Team for compliance with our posting guidelines, including verification of the company's legitimacy, accuracy of job details, clarity of remote work policy, and absence of misleading or fraudulent content.





