Lead- AI Engineer

Emplay; United States; Remote; USD 140,000 - 190,000; Full time

Job summary

Emplay is seeking a Lead AI Engineer to design and deliver production-grade LLM-powered features on AWS, build intelligent agents, and integrate enterprise tools. You will work with cross-functional teams to ship high-quality GenAI solutions at scale.

Ideal candidates bring 3-4 years in AI/ML engineering, hands-on LLM API experience, and strong Python/WASD cloud skills for scalable, secure, multi-region deployments.

Qualifications

• 3-4 years of AI/ML engineering experience.
• Hands-on with LLM APIs and building production-grade GenAI features.
• Strong knowledge of RAG pipelines, embeddings, and vector stores.
• Proficient in Python backend development (FastAPI/Flask).
• Experience with AWS services and cloud architectures.
• IaC experience with Terraform or AWS CDK and CI/CD pipelines.

Responsibilities

• Design, build, and deploy LLM-powered agents and conversational AI features on AWS.
• Architect and optimise end-to-end RAG pipelines including embeddings and vector stores.
• Implement MCP servers to support multi-agent orchestration workflows.
• Develop LLM evaluation frameworks for QA and regression tracking.
• Build scalable multi-region cloud infrastructure using core AWS services.
• Secure APIs with proper access controls and authentication flows.
• Integrate CRM, analytics tools via REST APIs and webhooks.
• Build bulk data ingestion/export pipelines with usage analytics.
• Own CI/CD pipelines and production reliability.
• Collaborate with product and engineering teams to scope and deliver features on time.

Tools

AWS Bedrock

OpenAI

Anthropic

LangChain

LlamaIndex

MCP

OpenSearch

Pinecone

pgvector

Python (FastAPI/Flask)

REST/GraphQL

OAuth 2.0 / SAML / OIDC

Terraform / AWS CDK

GitHub Actions

Job description

We are looking for a Lead- AI Engineer with hands-on experience in Generative AI, Retrieval-Augmented Generation (RAG), and AWS cloud services. You will work with teams to design and deliver production-grade LLM-powered features, build intelligent agents, and integrate enterprise tools — working closely with cross-functional teams to ship high-quality AI solutions at scale.

Key Responsibilities

• Design, build, and deploy LLM-powered agents and conversational AI features on AWS.
• Architect and optimise end-to-end RAG pipelines — embedding, vector indexing, and context retrieval.
• Implement Model Context Protocol (MCP) servers to support multi-agent orchestration workflows.
• Develop and maintain LLM evaluation frameworks for quality assurance and regression tracking.
• Build scalable, multi-region cloud infrastructure leveraging core AWS services.
• Secure APIs and enforce access controls, authentication flows, and data privacy standards.
• Integrate third-party platforms (CRM, Sales Enablement, analytics tools) via REST APIs and webhooks.
• Build bulk data ingestion/export pipelines and instrument usage analytics and logging.
• Own CI/CD pipelines, automated regression testing, and production reliability.
• Collaborate with product and engineering teams to scope, estimate, and deliver features on time.

Qualifications

• 3-4 years of experience AI/ML engineering or a related technical role, preferably in SaaS or a cloud-native environment.
• Hands-on experience with LLM APIs — AWS Bedrock, OpenAI, or Anthropic — and building production-ready GenAI features.
• Strong knowledge of RAG pipeline design — embeddings, vector stores (OpenSearch, Pinecone, pgvector),and retrieval strategies.
• Proficiency with agent frameworks such as LangChain or LlamaIndex; familiarity with MCP (Model Context Protocol).Solid AWS skills — Lambda, ECS/EKS, S3, DynamoDB,
• OpenSearch, SQS, and multi-region architecture patterns.
• Backend development in Python (FastAPI / Flask) — able to write and maintain production-quality services and APIs.
• REST / GraphQL API design with OpenAPI documentation; experience with OAuth 2.0, SAML, and OIDC.
• Infrastructure-as-code experience using Terraform or AWS CDK; CI/CD pipelines with GitHub Actions or equivalent.
• Strong problem-solving skills and ability to work with ambiguous requirements.
• Good communication skills, able to work with both technical and non-technical stakeholders.

Preferred Skills

• Experience with Sales Enablement or CRM integrations
• Familiarity with advanced agent orchestration and multi-tool LLM workflows.
• Prior experience in a B2B SaaS or enterprise software environment.