**Senior AI Engineer – LLM Systems & RAG Optimization
Location:** Remote (Global) Type: Full-Time or Contract Company: Texas Sports Academy
About Us
Texas Sports Academy is building the future of education for athletes. We combine elite athletic training with serious academics — and we’re scaling rapidly.
We already have a parent-facing AI SMS chatbot live in production. It works.
Now we need someone exceptional to make it world-class.
This is not a “call the OpenAI API” role. This is a systems, evaluation, and scaling role.
What You’ll Own
You will improve and scale our parent SMS AI chatbot used by thousands of families.
This includes:
- Optimizing and redesigning our RAG architecture
- Reducing hallucinations and irrelevant retrieval
- Improving latency and token efficiency
- Building robust evaluation pipelines
- Implementing LLM observability and monitoring
- Designing cost-efficient scaling infrastructure
- Improving conversation memory and routing logic
- Hardening guardrails for real-world usage
You will operate as the AI systems architect for this product.
Required Experience
You must have real production experience building and scaling LLM systems.
We’re looking for:
- 3+ years in applied ML or NLP
- Strong Python skills
- Deep experience with RAG systems
- Experience with vector databases (Pinecone, Weaviate, FAISS, etc.)
- Experience optimizing chunking & embedding strategies
- Experience evaluating LLM systems beyond subjective review
- Familiarity with LLM observability tools (LangSmith, Helicone, PromptLayer, etc.)
- Experience deploying scalable AI systems in production
You should be able to:
- Architect a full RAG pipeline from scratch
- Diagnose retrieval failures
- Build evaluation datasets
- Optimize for cost at scale
- Explain tradeoffs clearly
Bonus Points
- Experience with SMS-based AI systems
- Experience with multi-model routing
- Experience with context compression
- Startup experience
- Strong system design background
What Success Looks Like
Within 90 days:
- Hallucination rate meaningfully reduced
- Retrieval accuracy measurably improved
- Cost per conversation reduced
- Clear evaluation metrics implemented
- Observability dashboard live
- Scalable architecture roadmap in place
Take-Home Evaluation
You’ll be asked to:
Audit our existing SMS chatbot and deliver a structured improvement plan including:
- Architecture critique
- Retrieval optimization suggestions
- Hallucination reduction strategies
- Scaling plan
- Metrics & evaluation framework
- 30 / 60 / 90-day roadmap
Time expectation: 4–6 hours.
Compensation
Competitive. Open to global talent. Contract or full-time available.
If you’ve built real AI systems — not demos — we want to talk.
Job Type: Full-time
Pay: $250,000.00 - $300,000.00 per year
Work Location: Remote