LLM Developer Analyst

This is a fully remote position, open to applicants in Spain.

📋 Description

• We are seeking a highly proficient LLM Dev Analyst to design, develop, and scale intelligent agents within our Databricks ecosystem, transforming the way data is accessed, interpreted, and utilized throughout the organization.

• In this position, you will work at the convergence of AI engineering, analytics, and data platforms, creating domain-specific agents that automate and enhance decision-making across critical business areas such as A/B testing, marketing performance, data engineering workflows, and MarTech processes.

• You will convert intricate business challenges into agent-driven solutions powered by Large Language Models (LLMs), utilizing both structured and unstructured data to provide real-time insights and automation at scale.

• As a key contributor to our next-generation data stack, you will establish and implement best practices for agent architecture, prompt engineering, evaluation frameworks, and orchestration within Databricks, ensuring production-grade reliability and business impact.

• Key Responsibilities include:

1. Agent Design & Development

• - Create, build, and deploy LLM-powered agents for various business domains (A/B testing, marketing analytics, data engineering automation, MarTech workflows)

• - Develop multi-step reasoning agents that integrate with internal data systems, APIs, and tools

• - Implement RAG architectures to enable agents to effectively utilize enterprise data

2. Databricks & Data Integration

• - Integrate LLM agents within the Databricks lakehouse architecture

• - Construct scalable pipelines using PySpark, SQL, and Databricks workflows

• - Facilitate seamless interaction between agents and data warehouses, event streams, and APIs

3. Prompt Engineering & Evaluation

• - Design and refine prompts, tools, and agent workflows for accuracy and performance

• - Develop evaluation frameworks to assess agent quality, reliability, and business impact

• - Implement strategies to minimize hallucinations and enhance response consistency

4. Automation & Use Case Delivery

• - Create agents that automate:

• - Experimentation analysis (A/B testing insights)

• - Marketing performance reporting and optimization

• - Data Engineering workflows and monitoring

• - MarTech processes and campaign operations

• - Deliver solutions that yield measurable efficiency improvements and decision-making speed

5. Productionization & Reliability

• - Productionize agent systems with monitoring, logging, and observability

• - Implement guardrails, security controls, and governance frameworks

• - Ensure scalability, latency optimization, and cost effectiveness

6. Cross-Functional Collaboration

• - Collaborate with Data Engineering, Analytics, Marketing, and Product teams

• - Translate business requirements into scalable AI solutions

• - Communicate insights and capabilities to both technical and non-technical stakeholders

⛳️ Requirements

• Must-Have Qualifications:

• - Demonstrated experience in building applications with Large Language Models (LLMs)

• - In-depth expertise in prompt engineering, RAG architectures, and agent frameworks (e.g., LangChain, LlamaIndex)

• - Familiarity with Databricks/Snowflake/GCP, including PySpark and SQL

• - Strong proficiency in Python

• - Solid understanding of analytics use cases such as A/B testing, marketing performance, or data workflows

• - Experience implementing LLM evaluation, monitoring, and guardrails

• - Excellent problem-solving skills with the capability to translate business needs into technical solutions

• Nice-to-Have Qualifications:

• - Experience with vector databases (e.g., Pinecone, FAISS, Weaviate)

• - Knowledge of open-source LLM deployment and optimization (Hugging Face, vLLM, etc.)

• - Understanding of MLOps practices, CI/CD, and scalable infrastructure (Docker, Kubernetes)

• - Experience with MarTech tools (GA4, AppsFlyer, Segment, Braze, Amplitude)

• - Strong background in experimentation frameworks, causal inference, or incrementality

• - Experience designing multi-agent systems or autonomous workflows

• - Familiarity with AI product design and human-in-the-loop systems

• What We’re Looking For:

• - A builder mindset with a passion for applied AI and automation

• - Ability to thrive in ambiguous, fast-paced environments

• - Strong ownership and accountability for end-to-end delivery

• - Curiosity to explore and implement cutting-edge AI capabilities

• - A pragmatic approach to balancing innovation with reliability

🏝️ Benefits

• Growth and career development

• - At Leadtech, we prioritize your growth. Enjoy a flexible career path with personalized internal training and an annual budget for external learning opportunities.

• Work-Life balance

• - Benefit from flexible start and end times and the option of working fully remote or from our Barcelona office. Enjoy free Friday afternoons with a 7-hour workday, plus a 35-hour workweek in July and August so you can savor summer!

• Comprehensive benefits

• - Competitive salary, full-time permanent contract, and top-tier private health insurance (including dental and psychological services).

• - 25 days of vacation plus your birthday off, with flexible vacation options—no blackout days!

• Unique Perks

• - If you choose to work from our Barcelona office, you'll find it equipped with free coffee, fresh fruit, snacks, a game room, and a rooftop terrace with breathtaking Mediterranean views.

• - Additional benefits include restaurant and nursery vouchers, deducted directly from your gross salary.

• Equal Employment Opportunity Employer: Leadtech is an Equal Employment Opportunity (EEO) Employer, which means we promote applications from individuals with diverse backgrounds, interests, and personal circumstances. Our team welcomes applicants regardless of their race, gender, age, religion, nationality, sexual orientation, and/or disabilities.