AI Architect

MatchPoint Solutions is a fast-growing, young, energetic global IT-Engineering services company with clients across the US . We provide technology solutions to various clients like Uber, Robinhood, Netflix, Airbnb, Google, Sephora, and more! More recently, we have expanded to working internationally in Canada, China, Ireland, UK, Brazil, and India . Through our culture of innovation, we inspire, build, and deliver business results, from idea to outcome. We keep our clients on the cutting edge of the latest technologies and provide solutions by using industry-specific best practices and expertise.

We are excited to be continuously expanding our team. If you are interested in this position, please send over your updated resume. We look forward to hearing from you!

AI Architect
Whippany, NJ - Remote
12 Months
Pay rate: $120/hr - $125/hr on W2

Key Responsibilities

• Own the end-to-end delivery of greenfield generative and agentic AI solutions, from requirements discovery and architecture through implementation, testing, deployment, and operational support.
• Translate loosely defined business and operational challenges into clearly structured, working technical solutions.
• Personally develop production-quality AI applications and services using Python, Amazon Bedrock, foundation models, APIs, enterprise data sources, and cloud-native AWS services.
• Design agentic workflows that can ingest events, retrieve context, reason over evidence, select appropriate tools, execute approved actions, and validate results.
• Build retrieval-augmented generation solutions, including document ingestion, parsing, normalization, deduplication, semantic chunking, metadata enrichment, embedding generation, indexing, retrieval, reranking, citation, and access control.
• Design and implement hybrid-search and semantic-search solutions using OpenSearch Serverless, vector databases, or comparable platforms.
• Build deterministic processing, validation, policy enforcement, and workflow controls around LLM-based components.
• Integrate AI solutions with secured REST APIs, microservices, operational systems, event streams, databases, observability platforms, and enterprise applications.
• Develop ingestion and processing pipelines using services and technologies such as S3, AWS Glue, SQS, EventBridge, Lambda, PySpark, and streaming platforms.
• Implement production safeguards, including Bedrock Guardrails, prompt validation, grounding checks, sensitive-data protections, least-privilege IAM, authorization controls, audit logging, retries, timeouts, checkpointing, and dead-letter handling.
• Diagnose problems by correlating application logs, infrastructure metrics, model behavior, deployment changes, retrieved context, data quality, and other available technical signals.
• Design AI-assisted incident-triage and automation solutions that can classify severity, identify probable causes, retrieve similar incidents, recommend runbook actions, and produce evidence-supported outputs.
• Measure and optimize accuracy, retrieval quality, grounding, hallucination rate, latency, throughput, token consumption, infrastructure utilization, and operating cost.
• Establish evaluation methods and test datasets to validate that solutions perform reliably before production deployment.
• Use tools such as LangChain, CrewAI, Bedrock Agents, or custom orchestration code when appropriate, while understanding the underlying mechanics and tradeoffs of each approach.
• Use development accelerators such as Claude Code, Codex, and similar tools while maintaining accountability for architecture, code quality, security, and technical correctness.
• Clearly communicate architecture, data flow, design decisions, limitations, risks, and measurable business outcomes to both technical and nontechnical stakeholders.
• Produce concise technical documentation, operational runbooks, architecture diagrams, implementation plans, and support procedures. Required Qualifications
• 5+ years of professional software engineering or application development experience.
• 2+ years of hands-on experience designing and building generative AI or agentic AI solutions.
• Demonstrated experience personally delivering at least one AI solution from initial concept through working implementation.
• Advanced proficiency in Python and strong knowledge of software engineering principles, testing practices, error handling, object-oriented design, and maintainable application architecture.
• Hands-on experience building enterprise AI applications using Amazon Bedrock and Bedrock Runtime APIs.
• Experience selecting and integrating foundation models based on accuracy, latency, context-window, security, and cost requirements.
• Deep understanding of RAG architecture and implementation, including:
  • Document parsing and normalization
  • Metadata and permission preservation
  • Semantic chunking and overlap strategies
  • Embedding-model selection
  • Vector indexing and search
  • Hybrid retrieval
  • Reranking
  • Context assembly
  • Grounded-response generation
  • Retrieval and response evaluation
• Hands-on experience building agentic workflows with LangChain, CrewAI, Bedrock Agents, or custom orchestration frameworks.
• Experience designing tool-calling workflows that safely interact with APIs, databases, enterprise systems, or operational platforms.
• Experience with OpenSearch, vector databases, semantic search, or comparable retrieval technologies.
• Strong experience building APIs, microservices, and cloud-native applications.
• Experience with AWS services supporting data ingestion, event-driven processing, storage, security, monitoring, and deployment.
• Experience implementing AI security and governance controls, including IAM, data-access restrictions, sensitive-data handling, guardrails, auditability, and human approval points.
• Experience troubleshooting AI systems across the application, model, retrieval, data, infrastructure, and integration layers.
• Experience with Git, automated testing, CI/CD pipelines, infrastructure deployment, and modern DevOps practices.
• Ability to explain previous solutions in technical depth, including component interactions, architectural decisions, implementation challenges, tradeoffs, failures, improvements, and measurable results.
• Strong written and verbal communication skills. Preferred Qualifications
• Experience with Mantel Bedrock environments.
• Experience deploying or operating private and local models using Ollama, vLLM, or comparable technologies.
• Experience with Docker, Kubernetes, EKS, ECS, Lambda, or other container and serverless platforms.
• Familiarity with Apache Kafka, Kinesis, EventBridge, SQS, Fluent Bit, CloudWatch, or comparable event and observability technologies.
• Experience with document-processing technologies such as Amazon Textract, Apache Tika, or Unstructured.
• Experience developing AI-assisted incident management, alert triage, root-cause analysis, or operational automation solutions.
• Knowledge of MLOps, LLMOps, model evaluation, observability, red teaming, and production AI monitoring.
• Experience operating within regulated enterprise environments.
• Prior consulting or customer-facing technical-delivery experience.

MatchPoint Solutions provides equal employment opportunities to all employees and applicants for employment and prohibits discrimination and harassment of any type without regard to race, color, religion, age, sex, national origin, disability status, genetics, protected veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by federal, state or local laws.

This policy applies to all terms and conditions of employment, including recruiting, hiring, placement, promotion, termination, layoff, recall, transfer, leaves of absence, compensation, and training.