AceUp - Lead ML Engineer (Generative AI & LLM Focus)

Silver.com LLC

Job Overview

Location

Argentina

Job Type

Full-time

Full Job Description

📋 Description

• AceUp is undergoing a significant transformation, evolving from a traditional SaaS platform into a cutting-edge AI-first leadership development engine. We are seeking a highly skilled and motivated Lead ML Engineer with a strong focus on Generative AI and Large Language Models (LLMs) to spearhead this evolution. This is a unique opportunity to be at the forefront of integrating advanced AI capabilities into a user-facing product, bridging the gap between sophisticated machine learning intelligence and intuitive user experiences.
• As the primary developer responsible for bringing our new AI capabilities "to the glass," you will play a pivotal role in architecting and implementing the user-facing components of our AI-driven platform. While our dedicated ML team focuses on building the core intelligence in Python, your mission will be to translate this intelligence into tangible, interactive features. This involves designing and developing robust React frontends that users will engage with, and crafting the efficient Ruby backend logic that seamlessly orchestrates data flow between our established core platform and our new AI microservices.
• Our technology stack is deeply rooted in the Google Cloud Platform (GCP), and you will be building directly within this powerful ecosystem. Your responsibilities will span across various GCP services, including Vertex AI for generative AI and compute tasks, leveraging models like Gemini Pro/Ultra and the PaLM API, alongside Cloud Functions for serverless execution. You will work with data storage solutions such as Firestore and BigQuery, and utilize Vertex AI Vector Search for efficient data retrieval. Orchestration will be managed through Cloud Run and Pub/Sub, ensuring scalable and reliable operations. You will also be working with Python, LangChain, and LangGraph frameworks to build sophisticated AI applications.
• A core aspect of your role will be to architect and build state-of-the-art Conversational Agents. These agents will go beyond simple single-turn question-and-answer interactions, designed to maintain long-running, coherent dialogues. You will ensure these agents are stateful and context-aware, capable of handling complex reasoning tasks and providing a truly engaging conversational experience.
• You will be instrumental in building Retrieval Augmented Generation (RAG) pipelines. This involves developing low-latency retrieval systems that ground LLM responses in our proprietary data. The goal is to ensure high accuracy, relevance, and to significantly minimize the occurrence of hallucinations, providing users with trustworthy and reliable information.
• Furthermore, you will lead the development of advanced Natural Language Processing (NLP) pipelines. These pipelines will be designed to extract structured insights, such as semantic signals, sentiment analysis, and actionable items, from a variety of unstructured data sources, including text and potentially audio in the future.
• Implementing advanced personalization layers is another key responsibility. You will develop systems that dynamically adapt the behavior and tone of our AI models based on individual user history, preferences, and the current context, creating a tailored and highly effective user journey.
• You will own the end-to-end LLMOps and infrastructure for the models you deploy. This includes defining and managing prompt architecture, establishing robust evaluation frameworks, optimizing for latency, and carefully managing costs within the Vertex AI environment. Your expertise will ensure our AI services are performant, cost-effective, and reliable.
• Beyond individual contributions, you will serve as the technical "North Star" for our existing ML engineers. This mentorship role involves reviewing code, setting high architectural standards, and guiding technical decision-making. While you won't have direct people management responsibilities, your influence will be crucial in elevating the team's technical capabilities and ensuring alignment with our AI-first vision.
• We are looking for a "Product" Engineer who deeply cares about the end-user experience. Your focus will extend beyond mere accuracy to optimizing for utility, latency, and overall reliability in a production environment. You should be a GCP Specialist, comfortable navigating its services to build scalable and secure AI solutions. This is a hands-on architect role, where you are expected to code 70-80% of the time, thriving in the IDE rather than solely in meetings. You should be a Pragmatic Innovator, staying abreast of the latest research (e.g., LoRA, CoT, ReAct) but knowing when to apply simpler, proven solutions to deliver value quickly.

🎯 Requirements

• 6+ years of professional engineering experience, with a minimum of 3 years focused on Machine Learning/Natural Language Processing (ML/NLP) and at least 1 year specifically working with Large Language Models (LLMs) and Generative AI.
• Expert proficiency in Python. Strong familiarity with modern AI frameworks such as LangChain or LlamaIndex, and a solid understanding of Google Cloud Platform (GCP) services, particularly Vertex AI and Firestore.
• Excellent communication skills in conversational English. The ability to clearly articulate complex technical concepts, trade-offs, and solutions to both technical and non-technical stakeholders, including Product Managers and Executives, is essential.
• Bachelor of Science (B.S.) or Master of Science (M.S.) in Computer Science, Mathematics, or a related field, or equivalent practical experience demonstrating a strong foundation in computational principles.

🏖️ Benefits

• Opportunity to be a foundational member of an AI-first transformation at a growing company.
• Work with a modern, cutting-edge tech stack, including GCP, Vertex AI, Gemini, and advanced LLM frameworks.
• High degree of autonomy and impact in shaping the future of leadership development technology.
• Competitive salary and benefits package.
• Collaborative and innovative work environment with a focus on technical excellence and mentorship.

Skills & Technologies

Python

Ruby

React

GCP

Data Science

Senior

Onsite

Ready to Apply?

Apply Externally

You will be redirected to an external site to apply.

Silver.com LLC

Visit Website

About Silver.com LLC

Silver.com LLC is a U.S.-based precious metals dealer headquartered in Dallas, Texas. The company sells bullion, coins and bars in gold, silver, platinum and palladium for individual investors and retirement accounts. Orders are fulfilled through third-party vaulting partners and shipped insured nationwide. Services include price-locked online purchasing, IRA-approved storage programs and live market pricing data. Founded in 2014, the firm operates exclusively through its e-commerce platform and maintains an A+ BBB rating. Revenue derives from product markups over the spot price and storage fees, with no commission-based sales staff.

View Company Profile