1872 Consulting
Gen AI Solutions Architect
Total Compensation:
Up to $200K
Company Summary We are a digital engineering firm delivering production-grade AI, data, and platform solutions for enterprise clients in regulated industries. Our teams focus on building systems that ship, scale, and perform under real operational constraints. We value hands‑on ownership, technical rigor, and measurable outcomes over theory or advisory work.
Position Summary We are hiring a hands‑on Senior GenAI Solutions Architect to design, build, tune, and deploy production Generative AI systems. This is a delivery‑first role. You will personally implement GenAI pipelines, own architectural decisions through code, and be accountable for quality, latency, cost, and reliability in production environments. This is not a strategy or advisory role. Candidates must have recent experience writing code and shipping GenAI systems used by real users.
What You Will Do
Personally design, build, and deploy production GenAI applications and agentic systems.
Own end‑to‑end GenAI pipelines including data ingestion, embeddings, retrieval, orchestration, evaluation, and monitoring.
Implement and tune RAG pipelines, including chunking strategies, embeddings selection, hybrid search, reranking, and grounding.
Build and manage agentic workflows including task planning, tool invocation, memory handling, and failure recovery.
Tune model parameters, prompts, and retrieval logic to optimize response quality, latency, and cost.
Define and maintain evaluation frameworks including golden datasets, regression testing, and human‑in‑the‑loop review.
Diagnose and fix real production issues such as hallucinations, retrieval failures, latency spikes, and cost overruns.
Implement security, privacy, and governance controls including PII handling, auditability, and prompt‑injection defenses.
Produce clear architecture documentation tied directly to implemented systems.
Collaborate with product, security, and engineering teams to take systems from PoC to stable production.
What You Bring
10+ years of software engineering or solution architecture experience with recent hands‑on GenAI delivery.
Proven experience personally building and shipping multiple production GenAI systems.
Strong hands‑on coding skills in Python or TypeScript.
Deep experience with RAG architectures and retrieval optimization.
Experience building and operating agentic AI systems beyond simple chat flows.
Hands‑on experience with vector databases and embedding workflows.
Practical experience tuning LLM parameters and debugging model behavior.
Experience implementing evaluation, monitoring, and observability for GenAI systems.
Experience working in regulated or enterprise environments with strong governance requirements.
Ability to clearly explain technical trade‑offs and decisions.
Nice to Have
Model fine‑tuning or PEFT experience.
LangChain, LlamaIndex, or custom orchestration frameworks.
MLOps or LangOps experience for GenAI systems.
Experience optimizing token usage and inference cost at scale.
Not a Fit If
Your experience is primarily AI strategy, advisory, or consulting without direct implementation ownership.
You have not personally written and maintained GenAI production code.
Seniority level Mid‑Senior level
Employment type Full‑time
Job function Engineering and Information Technology
Industries IT Services and IT Consulting
Benefits
Medical insurance
401(k)
Vision insurance
#J-18808-Ljbffr
Up to $200K
Company Summary We are a digital engineering firm delivering production-grade AI, data, and platform solutions for enterprise clients in regulated industries. Our teams focus on building systems that ship, scale, and perform under real operational constraints. We value hands‑on ownership, technical rigor, and measurable outcomes over theory or advisory work.
Position Summary We are hiring a hands‑on Senior GenAI Solutions Architect to design, build, tune, and deploy production Generative AI systems. This is a delivery‑first role. You will personally implement GenAI pipelines, own architectural decisions through code, and be accountable for quality, latency, cost, and reliability in production environments. This is not a strategy or advisory role. Candidates must have recent experience writing code and shipping GenAI systems used by real users.
What You Will Do
Personally design, build, and deploy production GenAI applications and agentic systems.
Own end‑to‑end GenAI pipelines including data ingestion, embeddings, retrieval, orchestration, evaluation, and monitoring.
Implement and tune RAG pipelines, including chunking strategies, embeddings selection, hybrid search, reranking, and grounding.
Build and manage agentic workflows including task planning, tool invocation, memory handling, and failure recovery.
Tune model parameters, prompts, and retrieval logic to optimize response quality, latency, and cost.
Define and maintain evaluation frameworks including golden datasets, regression testing, and human‑in‑the‑loop review.
Diagnose and fix real production issues such as hallucinations, retrieval failures, latency spikes, and cost overruns.
Implement security, privacy, and governance controls including PII handling, auditability, and prompt‑injection defenses.
Produce clear architecture documentation tied directly to implemented systems.
Collaborate with product, security, and engineering teams to take systems from PoC to stable production.
What You Bring
10+ years of software engineering or solution architecture experience with recent hands‑on GenAI delivery.
Proven experience personally building and shipping multiple production GenAI systems.
Strong hands‑on coding skills in Python or TypeScript.
Deep experience with RAG architectures and retrieval optimization.
Experience building and operating agentic AI systems beyond simple chat flows.
Hands‑on experience with vector databases and embedding workflows.
Practical experience tuning LLM parameters and debugging model behavior.
Experience implementing evaluation, monitoring, and observability for GenAI systems.
Experience working in regulated or enterprise environments with strong governance requirements.
Ability to clearly explain technical trade‑offs and decisions.
Nice to Have
Model fine‑tuning or PEFT experience.
LangChain, LlamaIndex, or custom orchestration frameworks.
MLOps or LangOps experience for GenAI systems.
Experience optimizing token usage and inference cost at scale.
Not a Fit If
Your experience is primarily AI strategy, advisory, or consulting without direct implementation ownership.
You have not personally written and maintained GenAI production code.
Seniority level Mid‑Senior level
Employment type Full‑time
Job function Engineering and Information Technology
Industries IT Services and IT Consulting
Benefits
Medical insurance
401(k)
Vision insurance
#J-18808-Ljbffr