Insight Global
This range is provided by Insight Global. Your actual pay will be based on your skills and experience — talk with your recruiter to learn more.
Base Pay Range $70.00/hr - $80.00/hr
Responsibilities
Design and implement agentic architectures (single- and multi‑agent systems).
Build autonomous workflows: task decomposition, planning, and self‑correction loops.
Implement prompt engineering (system prompts, dynamic context building, tool‑calling protocols).
Build and consume APIs and microservices for agent tool use.
Deploy agentic systems within GitHub Enterprise environments, including secure secrets management, workflow automation, guardrail integration, compliance with enterprise governance, and monitoring agent behavior (telemetry, tracing, logs).
Define and run evaluations for agents covering task success, reliability, and safety metrics.
Debug and troubleshoot complex, tool‑using agent workflows.
Collaborate with product, data, and engineering teams to translate business needs.
Document agent designs, assumptions, limitations, and guardrails.
Qualifications
Strong understanding of LLMs, multimodal models, and transformer architectures.
Experience with fine‑tuning/adapting models (LoRA, RAG, prompt optimization, RLHF basics).
Hands‑on experience with agent frameworks (LangGraph, AutoGen, CrewAI, Semantic Kernel, Swarm).
Proficiency in Python and common AI/ML libraries (PyTorch, TensorFlow, OpenAI/Anthropic SDKs).
Experience building and consuming APIs and microservices for agent tool use.
Familiarity with event‑driven and asynchronous programming patterns.
Experience with RAG pipelines (embeddings, vector stores, retrieval optimization).
Knowledge of data engineering fundamentals (ETL, data quality, schema design for knowledge bases).
Deep experience with cloud platforms (Azure, AWS, GCP) for AI workloads, including model hosting, inference optimization, serverless and container‑based architectures, cost monitoring, and scaling strategies.
Proficiency in cloud‑native deployment architectures (Kubernetes, service meshes, managed inference endpoints).
Knowledge of grounding strategies to reduce hallucinations and enforce business rules.
Understanding of security, privacy, and responsible AI principles (PII handling, access controls, auditability).
Strong debugging and troubleshooting skills for complex, tool‑using agent workflows.
Ability to collaborate with product, data, and engineering teams to translate business needs.
Seniority Level Mid‑Senior level
Employment Type Full‑time
Job Function Information Technology
Industries Retail
Benefits
Medical insurance
Vision insurance
401(k)
Disability insurance
#J-18808-Ljbffr
Base Pay Range $70.00/hr - $80.00/hr
Responsibilities
Design and implement agentic architectures (single- and multi‑agent systems).
Build autonomous workflows: task decomposition, planning, and self‑correction loops.
Implement prompt engineering (system prompts, dynamic context building, tool‑calling protocols).
Build and consume APIs and microservices for agent tool use.
Deploy agentic systems within GitHub Enterprise environments, including secure secrets management, workflow automation, guardrail integration, compliance with enterprise governance, and monitoring agent behavior (telemetry, tracing, logs).
Define and run evaluations for agents covering task success, reliability, and safety metrics.
Debug and troubleshoot complex, tool‑using agent workflows.
Collaborate with product, data, and engineering teams to translate business needs.
Document agent designs, assumptions, limitations, and guardrails.
Qualifications
Strong understanding of LLMs, multimodal models, and transformer architectures.
Experience with fine‑tuning/adapting models (LoRA, RAG, prompt optimization, RLHF basics).
Hands‑on experience with agent frameworks (LangGraph, AutoGen, CrewAI, Semantic Kernel, Swarm).
Proficiency in Python and common AI/ML libraries (PyTorch, TensorFlow, OpenAI/Anthropic SDKs).
Experience building and consuming APIs and microservices for agent tool use.
Familiarity with event‑driven and asynchronous programming patterns.
Experience with RAG pipelines (embeddings, vector stores, retrieval optimization).
Knowledge of data engineering fundamentals (ETL, data quality, schema design for knowledge bases).
Deep experience with cloud platforms (Azure, AWS, GCP) for AI workloads, including model hosting, inference optimization, serverless and container‑based architectures, cost monitoring, and scaling strategies.
Proficiency in cloud‑native deployment architectures (Kubernetes, service meshes, managed inference endpoints).
Knowledge of grounding strategies to reduce hallucinations and enforce business rules.
Understanding of security, privacy, and responsible AI principles (PII handling, access controls, auditability).
Strong debugging and troubleshooting skills for complex, tool‑using agent workflows.
Ability to collaborate with product, data, and engineering teams to translate business needs.
Seniority Level Mid‑Senior level
Employment Type Full‑time
Job Function Information Technology
Industries Retail
Benefits
Medical insurance
Vision insurance
401(k)
Disability insurance
#J-18808-Ljbffr