LangChain Engineer

PTR Global; Jersey City (NJ); On-site; USD 180,000 - 260,000; Full time

Job summary

PTR Global is seeking a senior software engineer with 10+ years of experience to build advanced AI/ML applications on production systems. The role focuses on AI/ML skillsets using Java or Python and hands-on work with RAG architectures, vector stores, and orchestration frameworks. Onsite in Jersey City, NJ.

The ideal candidate will design prompts, implement voice and text chatbots, and work with AWS services, CI/CD, and microservices to deliver scalable AI solutions with strong governance.

Qualifications

• AI/ML skillset required with Java or Python
• 10+ years of software development experience in production
• Hands-on AI/ML production experience
• Strong knowledge of RAG architectures and vector stores
• Experience with AI orchestration frameworks
• Hands-on with AWS services and model invocation APIs
• Proven prompt engineering and guardrails practices
• Experience building conversational AI (text and voice)
• Familiarity with CI/CD, containers, and infra-as-code
• API design and microservices understanding

Responsibilities

• Develop AI/ML applications in production environments
• Architect and implement RAG-based solutions
• Experiment with embedding models and vector stores
• Leverage LangChain, LlamaIndex, Semantic Kernel or CrewAI for orchestration
• Work with AWS Bedrock and Claude models
• Design prompts and structured outputs for chat and voicebots
• Build and maintain REST/GraphQL APIs and microservices
• Ensure guardrails and responsible AI practices
• Collaborate with teams to deploy scalable AI services

Skills

AI/ML skillset

Java or Python

Tools

AWS Bedrock

LangChain

Docker

Kubernetes

Job description

Location:

Columbus, OH 43240 OR Plano, TX 75024 OR Jersey City, NJ 07310 (All days onsite)

***GC/ USC only*****

Must Have:

• AI/ML skillset - Java or python

Job Description:

• 10 plus years of software development experience (Java or Python).
• 2 plus years of hands-on experience building AI/ML applications in production.
• Strong proficiency with RAG architectures — chunking strategies, embedding models, vector stores (Pinecone, OpenSearch, pgvector, FAISS).
• Experience with AI orchestration frameworks: LangChain, LlamaIndex, Semantic Kernel, or CrewAI.
• Handson experience with AWS Bedrock, Anthropic Claude models, and model invocation APIs.
• Proven prompt engineering skills — system prompts, fewshot, chain-of-thought, tool use, structured outputs.
• Experience building conversational AI: chatbots (text) and voicebots (speechto-text, text-to-speech integration).
• Proficiency with AWS services (Lambda, Step Functions, API Gateway, S3, DynamoDB, SQS).
• Experience with CI/CD pipelines, containerization (Docker, ECS/EKS), and infrastructureas-code.
• Strong understanding of API design (REST, GraphQL), microservices architecture, and eventdriven systems.
• Familiarity with evaluation frameworks for LLM outputs.
• Experience with guardrails, content filtering, and responsible AI practices.