Lead AI Engineer

EPAM Systems; Brasil; Presencial; BRL 180 000 - 320 000; Tempo integral

Resumo da oferta

EPAM Systems in Brazil seeks a Lead AI Engineer to design, build and scale cutting-edge AI applications powered by large language models. You will partner with clients to deliver tailored LLM-driven solutions, architect agentic systems and drive adoption of emerging AI technologies across enterprise environments.

You will lead end-to-end AI projects, implement data pipelines and retrieval systems, evaluate model performance and ensure security, observability and compliance while driving adoption

Qualificações

• Experience with AI application development lifecycle including production deployment.
• Knowledge of vector databases, retrieval systems and ranking algorithms.
• Experience deploying AI solutions at scale with security and observability.

Responsabilidades

• Design, implement and maintain end-to-end AI applications and LLM-driven solutions.
• Collaborate with clients to understand needs and deliver tailored AI/LLM outcomes.
• Architect data pipelines, prompts, datasets and model evaluation strategies.
• Ensure performance, security, scalability and regulatory compliance.
• Prototype experiments to validate technical feasibility and business value.
• Stay current with MCP, A2A, ACP protocols and memory architectures.
• Develop and maintain APIs and system integrations for production AI apps.
• Deploy AI solutions at scale with guardrails and monitoring.
• Communicate complex concepts to both technical and non-technical stakeholders.

Conhecimentos

Python

Java

C#

Go

FastAPI

Streamlit

Gradio

LLM platforms

Prompt engineering

Ferramentas

LangChain

LangGraph

Semantic Kernel

LlamaIndex

Strands Agents

Descrição da oferta de emprego

We are seeking a Lead AI Engineer to design, build and scale cutting-edge AI applications powered by large language models. In this role, you will partner with clients to deliver tailored LLM-driven solutions, architect agentic systems and drive the adoption of emerging AI technologies across enterprise environments.

Responsibilities

• Design, implement and maintain end-to-end AI applications, including chatbots, Q&A platforms, agent workflows and other LLM-driven solutions
• Collaborate directly with clients to understand their needs, identify opportunities and recommend tailored AI/LLM solutions that drive business value
• Architect and optimize robust data pipelines, prompt strategies and datasets to ensure effective, accurate and scalable AI models
• Evaluate, monitor and refine AI system performance, ensure outputs are accurate, secure, scalable and compliant with industry regulations and best practices
• Conduct research, design experiments and perform rapid prototyping to validate technical feasibility and demonstrate the business value of AI solutions
• Stay current with evolving LLM technologies, frameworks, protocols (such as MCP, A2A, ACP) and methodologies, continuously improve solution quality and client outcomes
• Design and implement agentic systems with frameworks such as LangChain, LangGraph and Semantic Kernel, integrate with vector databases and advanced memory architectures
• Develop and maintain APIs and system integrations for production-grade AI applications, including enterprise system integration (CRM, ERP, databases)
• Deploy AI solutions at scale, consider performance, cost-efficiency, maintainability, observability and security (including guardrails and prompt injection prevention)
• Implement and monitor retrieval systems (keyword search, vector search, embeddings), ranking algorithms and agent evaluation frameworks
• Use MLOps/AIOps practices for agentic systems and ensure robust observability and monitoring of deployed solutions
• Clearly communicate complex technical concepts and AI strategies to both technical and non-technical stakeholders, iterate on models based on user feedback

Requirements

• Strong proficiency in at least one modern programming language (such as Python, Java, C#, Go, etc.); experience with web frameworks like FastAPI or similar is a plus
• Deep understanding of the AI application development lifecycle, including production deployment, system integration and rapid UI prototyping (Streamlit, Gradio or similar)
• Familiarity with major LLM platforms and APIs (OpenAI, Anthropic, Amazon Bedrock, Gemini) and related frameworks (LangChain, LangGraph, LlamaIndex, Strands Agents, etc.)
• Knowledge of advanced AI integration patterns (e.g., RAG, agent orchestration, tool calling), retrieval systems (keyword/vector search, embeddings) and ranking algorithms
• Experience to deploy AI solutions at scale, with a focus on performance, cost-efficiency, maintainability, observability and security (including guardrails and prompt injection prevention)
• Proven ability to evaluate generative AI quality with retrieval/classification scores, LLM-based evaluation, agent evaluation metrics and A/B testing
• Experience with vector databases (Pinecone, Weaviate, ChromaDB, FAISS) and semantic/hybrid search
• Experience to design experiments, conduct A/B tests and iterate on models based on user feedback
• Experience with enterprise system integration (CRM, ERP, databases) and deployment to cloud AI platforms or on-premise solutions
• Experience with observability and monitoring tools/frameworks, and application of MLOps/AIOps practices for agentic systems
• Familiarity with emerging protocols (MCP, A2A, ACP) and advanced memory architectures
• Proven experience in AI engineering and delivery of ML-based solutions in production environments
• Strong problem-solving skills, attention to detail and ability to work independently and collaboratively
• Excellent communication, collaboration and interpersonal skills, with the ability to explain complex technical concepts to non-technical stakeholders

Technologies

• Proficiency in at least one modern programming language (e.g., Python, Java, C#, Go, etc.) for AI development
• Web frameworks: FastAPI, Streamlit, Gradio, Flask, Spring Boot, ASP.NET or similar
• Major LLM platforms and APIs: OpenAI, Anthropic, Amazon Bedrock, Gemini
• Agentic frameworks: LangChain, LangGraph, Semantic Kernel, LlamaIndex, Strands Agents
• Data pipeline and integration tools
• Vector databases: Qdrant, FAISS, Chroma, Pinecone, Weaviate, ChromaDB
• Retrieval and ranking systems: keyword search, vector search, embeddings, ranking algorithms
• Cloud AI platforms: Azure OpenAI, Amazon Bedrock, GCP Vertex AI
• On-premise solutions: vLLM
• Enterprise AI platforms: AWS AgentCore, Databricks AgentBricks, Google Agents Space, Azure AI Foundry
• Observability and monitoring tools/frameworks
• MLOps/AIOps practices for agentic systems
• Security and guardrail tools for AI applications
• Protocols: MCP, A2A, ACP
• Advanced memory architectures

EPAM is an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, age, sexual orientation, gender identity or expression, disability, protected veteran status, or any other characteristic protected by applicable law.