Sobre

• Company Description
• Veritas Automata is a technology consulting and software development company dedicated to delivering innovative solutions that drive business success. We combine expertise in automation, AI, and advanced technology to enhance operational efficiency and streamline complex processes. Our teams build modern, intelligent, and scalable solutions that empower clients across regulated industries, enterprise platforms, and next-generation AI ecosystems. We are committed to innovation, ownership, and delivering measurable outcomes for our clients and partners.
• Yuxi Global, powered by Veritas Automata, is a South America-based delivery and talent entity that supports Veritas Automata’s global delivery model. We specialize in providing comprehensive solutions, including turnkey enterprise-grade application development, managed development teams, staff augmentation, and strategic consulting via our Veritas Automata Services Team.
• Job Description
• We are looking for an AI Engineer (L5) — a senior technical contributor responsible for building, optimizing, and operationalizing AI and LLM‑based applications, distributed agentic systems, and intelligent automation frameworks. With 5–8 years of experience, this role blends hands‑on engineering with architectural thinking, ensuring secure, scalable, and high‑performing AI solutions.
• You will design agent workflows, develop custom model integrations, build retrieval pipelines, implement guardrails, and collaborate closely with engineering, data, product, QA, and infrastructure teams. This role requires strong technical problem‑solving, structured thinking, and a deep understanding of how AI components integrate within distributed cloud‑native systems.

Core Responsibilities

• Design and implement AI/LLM‑powered capabilities including agent workflows, tool‑use actions, retrieval‑based systems, and structured output pipelines.
• Build integrations with major model providers (OpenAI, Azure OpenAI, Anthropic) and open‑source model ecosystems.
• Develop and optimize RAG pipelines, embeddings, vector search, and semantic retrieval patterns.
• Implement evaluation harnesses, guardrails, prompt management, and safety validation workflows.
• Collaborate with backend, frontend, and data engineers to deliver scalable AI‑driven features.
• Integrate AI capabilities into Kubernetes‑based microservices environments using modern APIs and deployment patterns.
• Configure and operate model‑serving environments (vLLM, TGI, KServe) including tuning for latency, throughput, and cost.
• Implement observability for AI systems including telemetry, metrics, traces, structured logs, and prompt evaluations.
• Support CI/CD automation, model versioning, feature flagging, and safe rollout of AI functionality.
• Contribute to documentation, architectural diagrams, and reusable internal AI patterns.
• Mentor junior engineers and support skill development across AI engineering best practices.
• Qualifications

Required qualifications

• 5–8 years of experience in software engineering, AI engineering, ML engineering, or distributed systems engineering.
• Hands‑on experience building AI/LLM applications including retrieval, embeddings, structured outputs, and function/tool calling.
• Strong proficiency in Python and TypeScript/JavaScript, including API development and workflow orchestration.
• Familiarity with agent frameworks (LangChain, LlamaIndex, DSPy, Semantic Kernel) and evaluation patterns.
• Experience with vector databases (FAISS, Milvus, Pinecone, Chroma) and semantic search pipelines.
• Working knowledge of Kubernetes, containers, Git‑based workflows, CI/CD, and cloud‑native deployment patterns.
• Strong understanding of distributed system design, performance tuning, and observability.
• Bachelor's degree in Computer Science, Engineering, Mathematics, or equivalent practical experience.
• Advanced English level (written and spoken) to communicate effectively across global teams.

Preferred experience

• Experience in regulated industries such as Life Sciences, healthcare, medical devices, or finance.
• Familiarity with multimodal model integration and real‑time inference workflows.
• Experience with GPU/accelerator‑based inference optimization and model‑serving performance tuning.
• Exposure to or contribution to agentic orchestration patterns and multi‑model coordination.
• Cloud certifications or AI/ML specialization credentials.
• Technical skills

AI Engineers at this level are expected to demonstrate familiarity with one or more tools and frameworks in each of the following categories

• Agent Frameworks & Orchestration
• LangChain, LlamaIndex, DSPy
• Semantic Kernel, tool/function calling patterns
• MCP‑based architectures and custom agent toolchains
• Programming & Data
• Python, TypeScript/JavaScript
• Pandas, NumPy, PySpark (awareness)
• Vector search (FAISS, Milvus, Pinecone)
• SQL/NoSQL databases
• Model Ops & Serving
• vLLM, TGI, KServe, Triton
• LoRA/adapters, prompt/version control
• Cost, latency, and performance optimization
• Observability & Telemetry
• Langfuse, Arize/Phoenix
• OpenTelemetry for LLMs
• Structured logs, traces, prompt evaluation
• Security & Governance
• Secrets management (Vault, KMS)
• Content filtering and policy enforcement
• PII/PHI handling, compliance‑aware design
• Soft Skills
• Strong communication skills and ability to collaborate across technical and non‑technical teams.
• Analytical thinking and structured problem solving.
• Ability to simplify complex AI concepts into clear implementation plans.
• High ownership mindset focused on quality, reliability, and measurable outcomes.
• Adaptability to rapidly evolving AI technologies and delivery environments.
• Mentorship capability to support junior engineers and cross‑functional partners.
• Organizational Competencies
• Remote Collaboration: Works effectively in distributed teams using asynchronous communication.
• Continuous Learning: Actively explores new models, frameworks, and safety techniques.
• Cultural Fit: Embodies Veritas Automata’s values of innovation, integrity, and ownership.
• Strategic Impact: Contributes reusable AI building blocks that accelerate future product delivery.
• Additional Information
• Workplace Conditions and Physical Expectations
• Prolonged periods of sitting at a desk and working on a computer.
• Must be able to lift 15 pounds at times.
• Must access and navigate each department at the organization’s facilities.
• Occasional travel to the client’s site may be required.
• Work-life integration: We support work-life balance and create greater synergy among work, home, family, and personal well-being.

• English Level: C1