S
AI Engineer / GenAI Solutions Architect (New York)
SRS Consulting
2 hours ago
Full-time
On-site
Senior AI Engineer / GenAI Solutions Architect
NYC, NY
Duration: 12+ Months Contract
Role Overview
The ideal candidate combines strong software engineering skills with deep understanding of LLMs, RAG, agents, context management, evaluation, and scalability.
Key Responsibilities
Solution Design & Architecture
Design end-to-end AI, RAG, and agentic solutions for enterprise use cases.
Evaluate architectural trade-offs and select appropriate patterns, models, and platforms.
Create and defend Architecture Decision Records (ADRs) and technical designs.
Identify risks, failure modes, scalability concerns, and optimisation opportunities.
AI Engineering & Development
Build production-grade AI applications using LLMs, agents, workflows, and retrieval systems.
Develop and integrate tools, APIs, vector databases, and knowledge systems.
Implement memory, context management, guardrails, evaluation, and observability capabilities.
Leverage AI-assisted coding tools (Claude Code, Cursor, GitHub Copilot, etc.) while maintaining engineering ownership of the solution.
Production Readiness
Improve consistency, reliability, and performance of AI systems.
Troubleshoot issues such as hallucinations, context bloat, latency, cost overruns, and output variability.
Design monitoring, testing, evaluation, and governance frameworks for production systems.
Optimize inference, retrieval, caching, and overall system performance.
Collaboration
Work with product, architecture, data, and platform teams to define and deliver solutions.
Translate business requirements into scalable technical architectures.
Contribute to engineering standards, best practices, and reusable AI assets.
Required Skills & Experience
Core AI & LLM Engineering
Hands-on experience building GenAI, RAG, and agentic applications.
Strong understanding of LLM architectures, prompting, model selection, and evaluation.
Experience with multi-agent systems, tool calling, MCP, workflow orchestration, or similar patterns.
Understanding of fine-tuning, embeddings, vector search, and retrieval architectures.
Architecture & System Thinking
Ability to justify technology choices and architectural decisions.
Experience designing solutions for enterprise-scale workloads and large data sets.
Strong understanding of scalability, reliability, cost, performance, and maintainability trade-offs.
Familiarity with Architecture Decision Records (ADR) and solution documentation.
Context & Memory Management
Understanding of:
Context management strategies
Context compression and summarization
Short-term and long-term memory patterns
Retrieval optimisation
Token and prompt efficiency
Engineering & Coding
Strong programming skills in Python and modern software engineering practices.
Experience with version control, testing, CI/CD, code reviews, and SDLC processes.
Ability to read, review, optimise, and troubleshoot AI-generated code.
Optimization & Production Operations
Understanding of:
KV Cache
Prompt caching
Response caching
Guardrails
Evaluation frameworks
Monitoring and observability
Performance optimisation techniques
What Success Looks Like
A successful candidate can confidently answer questions such as:
When should RAG be used instead of fine-tuning?
Why choose a multi-agent architecture versus a workflow?
How would you manage a million-token context?
Why is an AI agent producing inconsistent outputs?
Where should guardrails be implemented?
Would KV caching help in this scenario? Why and where?
What happens when retrieval quality degrades at enterprise scale?
Ideal Candidate Profile
We are looking for someone who is:
✅ A strong engineer first
✅ Experienced with production AI systems
✅ Comfortable with ambiguity and problem solving
✅ Able to reason about architectural trade-offs
✅ Curious, pragmatic, and continuously learning
✅ Capable of designing solutions, not just building demos
NYC, NY
Duration: 12+ Months Contract
Role Overview
The ideal candidate combines strong software engineering skills with deep understanding of LLMs, RAG, agents, context management, evaluation, and scalability.
Key Responsibilities
Solution Design & Architecture
Design end-to-end AI, RAG, and agentic solutions for enterprise use cases.
Evaluate architectural trade-offs and select appropriate patterns, models, and platforms.
Create and defend Architecture Decision Records (ADRs) and technical designs.
Identify risks, failure modes, scalability concerns, and optimisation opportunities.
AI Engineering & Development
Build production-grade AI applications using LLMs, agents, workflows, and retrieval systems.
Develop and integrate tools, APIs, vector databases, and knowledge systems.
Implement memory, context management, guardrails, evaluation, and observability capabilities.
Leverage AI-assisted coding tools (Claude Code, Cursor, GitHub Copilot, etc.) while maintaining engineering ownership of the solution.
Production Readiness
Improve consistency, reliability, and performance of AI systems.
Troubleshoot issues such as hallucinations, context bloat, latency, cost overruns, and output variability.
Design monitoring, testing, evaluation, and governance frameworks for production systems.
Optimize inference, retrieval, caching, and overall system performance.
Collaboration
Work with product, architecture, data, and platform teams to define and deliver solutions.
Translate business requirements into scalable technical architectures.
Contribute to engineering standards, best practices, and reusable AI assets.
Required Skills & Experience
Core AI & LLM Engineering
Hands-on experience building GenAI, RAG, and agentic applications.
Strong understanding of LLM architectures, prompting, model selection, and evaluation.
Experience with multi-agent systems, tool calling, MCP, workflow orchestration, or similar patterns.
Understanding of fine-tuning, embeddings, vector search, and retrieval architectures.
Architecture & System Thinking
Ability to justify technology choices and architectural decisions.
Experience designing solutions for enterprise-scale workloads and large data sets.
Strong understanding of scalability, reliability, cost, performance, and maintainability trade-offs.
Familiarity with Architecture Decision Records (ADR) and solution documentation.
Context & Memory Management
Understanding of:
Context management strategies
Context compression and summarization
Short-term and long-term memory patterns
Retrieval optimisation
Token and prompt efficiency
Engineering & Coding
Strong programming skills in Python and modern software engineering practices.
Experience with version control, testing, CI/CD, code reviews, and SDLC processes.
Ability to read, review, optimise, and troubleshoot AI-generated code.
Optimization & Production Operations
Understanding of:
KV Cache
Prompt caching
Response caching
Guardrails
Evaluation frameworks
Monitoring and observability
Performance optimisation techniques
What Success Looks Like
A successful candidate can confidently answer questions such as:
When should RAG be used instead of fine-tuning?
Why choose a multi-agent architecture versus a workflow?
How would you manage a million-token context?
Why is an AI agent producing inconsistent outputs?
Where should guardrails be implemented?
Would KV caching help in this scenario? Why and where?
What happens when retrieval quality degrades at enterprise scale?
Ideal Candidate Profile
We are looking for someone who is:
✅ A strong engineer first
✅ Experienced with production AI systems
✅ Comfortable with ambiguity and problem solving
✅ Able to reason about architectural trade-offs
✅ Curious, pragmatic, and continuously learning
✅ Capable of designing solutions, not just building demos