Senior Forward Deployed Engineer

About the role

Senior Forward Deployed Engineer (AI/LLM, Full Stack)

Manhattan New York On Site

Contract

Competitive rate

You must hold full working rights in the United States. We're unable to sponsor visas for this role.

About the role

We're looking for a Senior Forward Deployed Engineer to embed into our client working alongside our AI Solutions Lead, building production AI applications directly.

You'll partner with clients to understand their operational problems, then design and ship full-stack solutions powered by LLMs and agentic workflows. This isn't a back-office build role. You'll be onsite, owning projects from discovery through deployment and iterating fast as requirements shift.

What you will do

Work directly with our client to scope problems and turn them into technical solutions

Build and deploy production-ready applications with modern full-stack tooling

Develop LLM features, AI agents, and intelligent workflows inside customer environments

Build backend services and frontend experiences that hold up under real use

Run prompt engineering and evaluation cycles to keep improving what's shipped

What you will bring

Solid background in software engineering / AI Engineering

Strong full-stack skills in Python and/or TypeScript, plus React and SQL

Hands-on experience shipping LLM or generative AI applications in production

Working knowledge of AI agents, agentic workflows, prompt engineering, RAG, and evals

Comfortable translating business needs into technical decisions with minimal hand-holding

Strong communication skills. You'll be the engineer customers see and trust

TECH SKILLS

Core Languages & Backend

Python: Non-negotiable for AI orchestration, data scripting, and backend logic.

TypeScript / Node.js: Essential for building customer-facing extensions, full-stack glue code, and lightweight web UIs.

SQL & Java/Go: Vital for deep database queries and heavy enterprise system extensions.

FastAPI / Flask: For spinning up microservices and rapid integration layers on-site.

AI & Agent Orchestration

LLM Providers: Fluency with Anthropic Claude, OpenAI, and open-source models via Hugging Face or vLLM.

Orchestration: Production proficiency in LangChain or LangGraph and CrewAI for building multi-step agent behaviours.

RAG & Vector Stores: Hands-on design with vector databases (Pinecone, Qdrant, pgvector) and retrieval systems.

Evaluation & Observability: Rigorous deployment tracking using tools like LangSmith or Braintrust to audit hallucination rates and latency.

Data & Infrastructure

Databases & Warehouses: PostgreSQL, Snowflake, or BigQuery for customer data ingestion.

Cloud Platforms: Working knowledge of AWS, GCP, or Azure.

Containerisation: Docker as a baseline, alongside basic Kubernetes and Terraform for replicating environments in