Generative AI Engineer

GEN AI ENGINEERs - RAG, Bedrock, LangChain, Advanced Python, AWS Serverless, Weaviate

5 Roles available (remote in US EST 9 am - 5 pm)

You will work directly with clients to design, build, and deploy sophisticated Generative AI solutions - including RAG systems, multi-agent orchestrations, and automated document processing - within an agile, high-impact environment.

Technical Skill Priority Matrix Success in this role is defined by deep hands-on expertise. Candidates will be evaluated based on the following priority levels: 1. Critical Must-Haves (Tier 1) Amazon Bedrock:

Proven experience with foundation models (Claude, Nova, Llama), model invocation, streaming, and guardrails. Agent Frameworks:

Hands-on production experience with LangChain, LlamaIndex, or Bedrock Agents. Advanced Python:

Mastery of Python 3.9+ (Async/Await, type hinting) and robust testing (pytest). AWS Serverless:

Building event-driven architectures using Lambda, API Gateway, and Step Functions. Vector Databases:

Implementation of semantic search using Weaviate, OpenSearch, or Pinecone. 2. Highly Valued (Tier 2) Advanced Bedrock:

Experience with AgentCore (Memory, Gateway, Observability). Data Modeling:

Single-table design in DynamoDB and complex orchestration via AWS Step Functions. DevOps/Data Ops:

Containerization (Docker/ECS) and data manipulation via Pandas or PySpark. 3. Differentiators (Tier 3 & 4) RAG Architecture:

Advanced chunking strategies and context management. IaC:

Infrastructure-as-Code proficiency using AWS CDK or Terraform. Observability:

Distributed tracing and monitoring for AI (CloudWatch/X-Ray). Specialized ML:

SageMaker endpoints and model fine-tuning (PEFT).

Primary Responsibilities GenAI Engineering:

Develop production-ready AI agents and conversational interfaces using LLM APIs (Anthropic, OpenAI) and advanced prompt engineering. Cloud Architecture:

Design and implement serverless backends and RESTful/WebSocket APIs to support real-time AI interactions. Data Pipeline Development:

Build end-to-end ingestion and transformation workflows for structured and unstructured data, ensuring high-quality embeddings for retrieval. Client Delivery:

Translate complex business requirements into technical specs, participate in agile ceremonies, and provide high-level technical guidance to stakeholders.

Required Experience & Qualifications Software Engineering:

5+ years of total experience; minimum

2 years

focused on AI/ML or Cloud-native development. AWS Expertise:

2+ years of hands-on production experience in the AWS ecosystem. GenAI Focus:

1+ years of direct experience with LLMs, RAG, and AI agents. Communication:

Exceptional English verbal and written skills for direct client interaction. Independence:

A proven track record of delivering complex projects with minimal supervision in a distributed team. Preferred:

AWS Certifications (Solutions Architect or ML Specialty) and experience in regulated industries (Healthcare/Finance).

We are an

Equal Opportunity Employer . We celebrate diversity and are committed to creating an inclusive environment for all employees. All employment decisions are based on business needs, job requirements, and individual qualifications, without regard to race, color, religion, gender, sexual orientation, national origin, genetics, disability, age, or veteran status.