Senior AI Engineer (RAG/LLM)

About Trustero

Trustero is an advanced AI application, purpose-built for the Security and Compliance vertical. Our patented AI agents can accurately and consistently do the most time-consuming jobs in Governance, Risk, and Compliance, like perform gap analysis, provide remediation guidance, questionnaire automation, evidence collection + mapping, and more, saving companies hundreds-of-thousands of dollars and returning 100s of valuable working hours each month.

Role Overview

As a Senior AI Engineer at Trustero, you will play a crucial role in optimizing/evaluating large language models (LLMs) for reasoning and decision-making processes, as well as implementing RAG pipelines and agentic architectures/workflows.

You will work closely with our engineering team to implement cutting-edge LLM/RAG techniques that enhance the intelligence and performance of our AI driven Governance, Risk and Compliance platform.

The ideal candidate has hands-on experience integrating LLMs and working with RAG pipelines, and is passionate about applying these technologies to deliver tangible impact. Familiarity with NLP and ML methods—particularly text classification—or experience fine-tuning LLMs for specific industry verticals would be highly desirable.

Salary Range: $150,000 - $220,000 USD per year, plus stock options, based on experience and qualifications.

Key Responsibilities

• LLM Integration & Reasoning

  • Develop LLM-based reasoning techniques, including automated decision-making and context understanding.

  • Integrate LLM solutions into the core product to enhance user experiences and streamline compliance workflows.

• RAG Pipeline & Optimization

  • Proficiency in chunking large documents and creating efficient indexes for retrieval-augmented generation.

  • Experience running queries on RAG databases or vector stores to retrieve relevant context.

  • Skill in re-ranking and optimizing results to provide the highest-quality context for LLM queries.

• Collaboration & Engineering

  • Collaborate with the engineering team to integrate LLM solutions into our infrastructure, ensuring compatibility and scalability.

  • Partner with product managers and engineers to align functionality with the product vision and deliver tangible user value.

  • Conduct code reviews, write clean, maintainable code, and follow software engineering best practices.

• Continuous Improvement

  • Continuously experiment with cutting-edge ML techniques and frameworks, particularly those related to LLMs and emerging technologies.

  • Monitor and evaluate LLM system performance in production, iterating on solutions and model selection to ensure high reliability.

Salary Range: $150,000 - $220,000 USD per year.

Requirements

• 5+ years of software engineering experience with a focus on ML, NLP, LLMs, or RAG.

• Bachelor’s degree in Computer Science, Software Engineering, or a related field (advanced degrees are a plus).

• Proven track record with large language models (LLMs), applying them to reasoning and decision-making tasks.

• Expertise in LLM pipelines and RAG frameworks (e.g., Haystack, LlamaIndex, LangChain) and strong programming skills in Python or similar languages.

• Solid understanding of cloud platforms (AWS, GCP, or Azure) for production deployment and performance monitoring.

• Excellent collaboration and communication skills, able to work effectively with cross-functional engineering teams.

• Strong problem-solving abilities, adept at navigating complex technical challenges in a fast-paced environment.
  

Preferred Qualifications

• Proficiency in Go, TypeScript, gRPC, and Protocol Buffers (Protobuf).

• Hands-on experience with LLM model tuning and performance benchmarking.

• Familiarity with NLP and ML techniques for text classification.

• Exposure to compliance, governance, or security-related platforms.

• Knowledge of microservices architecture, DevOps, and containerization tools (Docker, Kubernetes).