GenAI Engineer

Siri InfoSolutions Inc; Plano (TX); On-site; USD 130,000 - 170,000; Full time

Job summary

Siri InfoSolutions Inc. is seeking a Gen AI engineer to design and implement enterprise-grade AI solutions on AWS Bedrock.

You will build scalable workflows, develop RAG-based retrieval systems, and optimize prompts, memory, and grounding while collaborating with security and architecture teams. You will also integrate MCP-based tools, manage latency and cost efficiency, and ensure high-quality, compliant model outputs across enterprise workloads.

Qualifications

• Enterprise Gen AI experience with scalable systems.
• Hands-on with AWS Bedrock and related AWS services.
• Knowledge of embeddings, RAG, and vector search.
• Experience with prompt engineering and context management.
• Familiarity with MCP concepts and tool integration.
• Strong Python or Java development skills.

Responsibilities

• Design and implement Gen AI apps using AWS Bedrock and related services.
• Build scalable AI workflows for enterprise use cases.
• Develop retrieval-augmented generation solutions leveraging enterprise knowledge sources.
• Manage context windows, memory strategies, prompts, and grounding techniques.
• Integrate MCP-based tools and services to extend model capabilities.
• Collaborate with product owners, architects, data engineers, and security teams.
• Evaluate model outputs for quality, safety, relevance, and factual accuracy.
• Optimize latency, cost, and token usage across AI workloads.
• Create reusable prompts, agent patterns, and orchestration components.
• Support deployment, monitoring, logging, and continuous improvement of Gen AI systems.

Skills

Python

Java

Gen AI

Prompt engineering

LangChain

API design

Cloud services

Tools

AWS Bedrock

OpenSearch

Aurora PostgreSQL

DynamoDB

LangGraph

Vector databases

Job description

Roles & Responsibilities:

• Design and implement Gen AI applications using AWS Bedrock and related AWS services.


• Build secure, scalable, and maintainable AI workflows for enterprise use cases.


• Develop retrieval-augmented generation solutions that use enterprise knowledge sources effectively.


• Manage context windows, memory strategies, prompt composition, and grounding techniques.


• Integrate MCP-based tools and services to extend model capabilities and connect to enterprise systems.


• Collaborate with product owners, architects, data engineers, and security teams.


• Evaluate model outputs for quality, safety, relevance, and factual accuracy.


• Optimize latency, cost, and token usage across AI workloads.


• Create reusable prompts, agent patterns, and orchestration components.


• Support deployment, monitoring, logging, and continuous improvement of Gen AI systems.


• Strong experience with Python or Java.


• Hands-on experience with AWS Bedrock.


• Understanding of foundation models, embeddings, RAG, and vector search.


• Experience with prompt engineering and context management.


• Familiarity with MCP concepts and tool integration patterns.


• Experience with APIs, microservices, and cloud-native architecture.


• Knowledge of enterprise security, privacy, and governance requirements.


• Ability to evaluate model performance and improve response quality.


• Good communication and stakeholder collaboration skills.

Generic Managerial Skills, If any:

• Experience with LangChain, LangGraph, or similar orchestration frameworks.


• Experience with OpenSearch, Aurora PostgreSQL, DynamoDB, or vector databases.


• Knowledge of IAM, KMS, CloudWatch, Lambda, Step Functions, and API Gateway.


• Experience with agentic workflows and tool-calling architectures.


• Familiarity with software engineering best practices, testing, and CI/CD.


• Automotive or manufacturing domain experience is a plus