GenAI Engineer

Role Overview

• Design, implement, and maintain complex enterprise solutions based on Generative AI, Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG).
• Act as the guardian of quality and robustness for our GenAI solutions, leading the implementation of our standardized methodology.
• Work directly with enterprise clients to translate complex business problems into scalable, reliable GenAI architectures.
• Design end-to-end architectures for RAG systems, conversational agents, multi-agent systems, and content-generation solutions.
• Make critical technical decisions about approach, LLM selection, vectorstores, and retrieval strategies based on each project's specific requirements.
• Build complete RAG pipelines including document loaders, optimal chunking strategies, metadata enrichment, embeddings, vectorstores, hybrid search, re-ranking, and generation with LLMs.
• Optimize each component to maximize relevance, groundedness, and performance.
• Design, iterate, and optimize complex prompts using advanced techniques.
• Design and implement ingestion, processing, and structuring pipelines for diverse knowledge sources.
• Implement comprehensive evaluation frameworks combining automated metrics and human evaluation.
• Integrate robustly with models such as GPT-4, Claude, Gemini, Llama, and Mistral using APIs.
• Manage deployments on cloud platforms optimized for latency, cost, and scalability.
• Implement continuous monitoring systems for quality metrics and operational efficiency.
• Continuously analyze and optimize token consumption and compute resource usage.
• Implement robust security measures and ensure compliance with GDPR and local regulations.

Requirements

• 3+ years of hands-on experience designing and implementing production solutions based on Large Language Models, including RAG systems, conversational agents, and content-generation workflows.
• Proven experience taking GenAI projects from discovery to production.
• Advanced experience with frameworks such as LangChain, LlamaIndex, or similar.
• Deep knowledge of LLM platforms (OpenAI API, Anthropic Claude, Google Gemini) and their capabilities including function calling, structured outputs, and JSON mode.
• Strong experience implementing end-to-end RAG architectures including document processing, chunking strategies, embedding models (OpenAI, sentence-transformers), vectorstores (Pinecone, Chroma, Weaviate, pgvector), retrieval strategies (semantic search, hybrid search, re-ranking), and generation patterns.
• Demonstrated ability designing and optimizing complex prompts using advanced techniques (few-shot, chain-of-thought, ReAct).
• Experience implementing effective guardrails against hallucinations, including grounding, citation enforcement, and validation post-processing.
• Familiarity with multi-agent frameworks such as AutoGen, CrewAI, or LangGraph to orchestrate complex workflows.
• Strong programming skills in Python with experience building scalable applications.
• Knowledge of architectural patterns (microservices, event-driven), RESTful APIs, and software engineering best practices (testing, CI/CD, version control).
• Experience deploying ML pipelines to production including model serving, monitoring, logging, and continuous evaluation.
• Familiarity with containerization (Docker), orchestration (Kubernetes), and infrastructure-as-code (Terraform).
• Practical experience with cloud AI/ML services on AWS (Bedrock, SageMaker), Google Cloud (Vertex AI), or Azure (OpenAI Service).
• Experience processing unstructured data (PDFs, documents, HTML), structured data (databases, APIs), and semi-structured sources.
• Experience implementing evaluation frameworks for GenAI systems using automated metrics, human evaluation, and benchmarking.
• Knowledge of security best practices in GenAI including prompt-injection defenses, PII protection, access control, and audit logging.
• Exceptional ability to communicate complex technical concepts to diverse audiences, present architectures and trade-offs to executive stakeholders, and produce clear, comprehensive technical documentation.
• Ability to translate business requirements into technical solutions, define success metrics aligned with business objectives, and optimize solutions to maximize ROI and customer value.
• Experience in technical consulting or customer-facing roles, with the ability to run discovery sessions, manage expectations, and communicate risks and opportunities transparently.
• Ability to communicate effectively in technical English, both written and verbal, for collaboration with international teams and reading technical documentation.

Tech Stack

• AWS
• Azure
• Cloud
• Docker
• Kubernetes
• Python
• React
• Terraform

Benefits

• 100% remote work with hours aligned to CST.
• Unlimited PTO: We trust you to manage your time effectively.
• Annual development budget: Access to courses, certifications, and conferences.
• Equipment budget: Set up your ideal remote workspace.
• Semi-annual performance bonuses: We recognize and reward your impact with financial incentives.
• Health benefit: Access to private medical coverage or subsidies for health insurance.
• Growth opportunities: Career plan and mentorship with AI and technology experts.
• Dynamic, flexible startup environment: Autonomy to make decisions and propose ideas, with a focus on results rather than hours worked.
• Work-life balance: A culture that prioritizes flexibility and well-being, allowing you to manage your time without sacrificing personal life.