Senior AI Coach (AI & LLM Enablement) at Applaudo Studios

San Salvador, San Salvador, El Salvador -

Full Time

Start Date

Immediate

Expiry Date

07 May, 26

Salary

0.0

Posted On

06 Feb, 26

Experience

5 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

Skills

AI Professional, LLM-Powered Systems, Team Enablement, Generative AI Adoption, Python Engineering, API Design, LLM Experience (OpenAI, Anthropic, Google, Llama, Mistral), RAG Systems, Embeddings, Vector Stores, Tool/Function Calling, Lightweight Fine-tuning (LoRA/PEFT), LLM Evaluation, AI Safety and Guardrails, Facilitation Skills, LLMOps/MLOps

Industry

IT Services and IT Consulting

Description

Job Description About You You are a highly skilled AI professional who thrives at the intersection of engineering, solution design, and team enablement. You excel at building real-world LLM-powered systems while also mentoring, coaching, and uplifting cross-functional teams. You are passionate about helping organizations adopt Generative AI responsibly and effectively, and you communicate complex AI behaviors in simple, actionable ways. You enjoy working with cutting-edge models, designing scalable architectures, and empowering others through hands-on training, paired programming, and internal playbooks. You Bring to Applaudo the Following Competencies: Bachelor’s Degree in Computer Science, Software Engineering, Data Science, or equivalent experience (preferred). 5+ years of software engineering experience, with 1–3+ years specifically working with Generative AI/LLMs. Strong Python engineering skills including API design, testing, CI/CD, and containerization. Practical hands-on experience with LLMs such as OpenAI/Azure OpenAI, Anthropic, Google, and open-source models like Llama or Mistral. Proven experience building RAG systems, embeddings, vector stores, tool/function calling, and lightweight fine-tuning (LoRA/PEFT). Experience evaluating LLM systems using rubric-based evaluation, prompt regression tests, telemetry/tracing, and A/B testing. Familiarity with AI safety and guardrails, including content moderation, prompt injection mitigation, output validation, and PII protection. Strong facilitation skills such as leading workshops, training sessions, pair programming, and creating technical enablement materials. Excellent communication skills and the ability to explain probabilistic and non-deterministic system behavior. Experience with LLMOps/MLOps (experiment tracking, model versioning, monitoring, rollback strategies). (Nice to Have) Knowledge of retrieval and data design (chunking, indexing, metadata), vector observability tools (Langfuse, OpenTelemetry), and privacy/security frameworks (GDPR, SOC 2). (Nice to Have) Exposure to Azure Cloud, multimodal models, JSON schema outputs, agent orchestration, and product-first thinking. (Nice to Have) Advanced English level, as you will collaborate with teams and stakeholders across regions. You Will Be Accountable for the Following Responsibilities: Facilitate discovery workshops to identify, evaluate, and prioritize high-impact Generative AI use cases aligned with business objectives. Define technical architectures for LLM solutions, including RAG pipelines, agent/tool orchestration, and structured output workflows, ensuring compliance and security requirements are met. Build prototypes and production-grade AI services using LLM APIs and open-source models, applying best practices in scalability, reliability, and cost optimization. Implement retrieval pipelines, embeddings, prompt orchestration, function/tool calling, and validation layers to ensure high-quality outputs. Establish evaluation frameworks—including prompt tests, rubric scoring, telemetry, tracing, and A/B testing—to measure performance, reliability, and drift. Implement safety and governance controls such as content moderation, PII protection, prompt injection mitigation, and red-teaming practices. Create model cards, documentation, usage guidelines, and responsible AI processes to support transparency and compliance. Lead training sessions, office hours, and pair-programming activities to enable engineering teams and uplift internal AI capabilities. Develop internal playbooks covering prompting strategies, RAG workflows, evaluation harnesses, and deployment best practices. Advise on operating models, LLMOps processes, and organizational readiness for Generative AI adoption. Collaborate with product, engineering, data, and compliance teams to define success metrics, milestones, and delivery plans for AI initiatives. Document system architectures, runbooks, and technical handover materials to ensure sustainable, long-term knowledge transfer. Additional Information Here at Applaudo values as trust, communication, respect, excellence and team work are our keys to success. We know we are working with the best and thus treat each other with respect and admiration without asking. Submit your application today, and don't miss this opportunity to join the Best Digital team in the Region! We truly appreciate all the hard and outstanding work our team makes every day at Applaudo Studios, and that's why the perks that we offer, are deeply thought and designed as a way to thank them for their commitment and excellence. Some of our perks and benefits: Celebrations Special discounts* Entertainment area* Modern Work Spaces* Great work environment Private medical insurance* *Benefits may vary according to your location and/or availability. Request further information when applying.

Responsibilities

The role involves facilitating workshops to define high-impact Generative AI use cases and architecting technical solutions for LLM systems, including RAG pipelines and agent orchestration. Responsibilities also include building production-grade AI services, establishing robust evaluation frameworks, and implementing necessary safety and governance controls.