GenAI Engineer – Production AI & RAG (Remote)

Xactus; Broomall (PA); On-site; USD 120,000 - 170,000; Full time

Benefits offered by this job

Medical, vision, dental

Bonus programs

Fitness reimbursement

401k with company match

Disability insurance

Life insurance

Legal services

Employee discounts

Job summary

Xactus is hiring an AI Engineer (GenAI Features) to design, build, and deploy production-gen AI applications. You will translate GenAI concepts into customer-facing and internal features using LangChain, LangSmith, and Agentcore, with strong retrieval architectures.

You’ll collaborate with DevOps and data teams to ensure scalable, reliable solutions across the stack. The role requires experience with ML frameworks, AWS, Python, and FastAPI, plus a track record of shipping GenAI features.

Qualifications

• Bachelor’s degree in related field or equivalent.
• 3–5 years building production AI/ML systems or full-stack applications; experience with ML/AI frameworks such as PyTorch, TensorFlow, scikit-learn.
• 1–2+ years with LangChain, LangSmith, or similar LLM frameworks; hands-on with Claude and/or GPT models.
• 2+ years of AWS experience (S3, CloudFormation, CloudWatch). Strong Python and FastAPI; SQL expertise; RAG and semantic search experience.
• Highly preferred: AWS Bedrock, Codex/code generation models, prompt engineering at scale, GraphRAG/Neo4j/Neptune, deep learning, NLP, Terraform, Docker/Kubernetes, MLflow, OpenSearch, AWS Glue; track record of shipping GenAI features.

Responsibilities

• GenAI feature development: build production GenAI applications using LangChain, LangSmith, and Agentcore; implement complex agent workflows.
• RAG & GraphRAG architecture: design retrieval-augmented generation systems and knowledge graphs for reasoning.
• Data pipeline & ETL development: write Python ETL scripts; design data models for graph databases; collaborate on AWS Glue and S3 management.
• Database & query optimization: optimize Cypher/SPARQL queries and vector search.
• Backend API development: build production FastAPI services with robust error handling and fallbacks.
• Model tracking & experimentation: use MLflow for versioning and metrics; monitor LLM outputs for quality and bias.
• Production monitoring & debugging: implement logging/metrics/tracing with CloudWatch and LangSmith; respond to incidents.
• Code quality & testing: write unit/integration tests; conduct code reviews; validate AI outputs.
• Cross-functional collaboration: work with DevOps, data engineers, and product teams to translate requirements into designs.
• Documentation & knowledge sharing: document architectures and runbooks; share learnings on patterns and prompt engineering.

Skills

Strong communication

LLM mastery

Problem solving

Production reliability

Cross-functional collaboration

Education

Bachelor’s degree or equivalent

Tools

LangChain

LangSmith

Agentcore

Neo4j/Neptune

OpenSearch

PyTorch

TensorFlow

scikit-learn

FastAPI

MLflow

AWS (S3, CloudWatch)

Docker/Kubernetes

Job description

Xactus is hiring an AI Engineer (GenAI Features) to design, build, and deploy production-gen AI applications. You will translate GenAI concepts into customer-facing and internal features using LangChain, LangSmith, and Agentcore, with strong retrieval architectures.

You’ll collaborate with DevOps and data teams to ensure scalable, reliable solutions across the stack. The role requires experience with ML frameworks, AWS, Python, and FastAPI, plus a track record of shipping GenAI features.