AI Engineer – Backend

Job Title: AI Engineer – Backend

Location: New York City, New York (3 days onsite from day 1)

EST Candidates Only

(LangChain/Vertex/Bedrock & Enterprise AI Solutions)

Role Overview:

Client is seeking a highly skilled AI Engineer (Backend) to architect and implement scalable, secure, and modular AI solutions across the company. This role will focus on building enterprise-grade AI applications using industry standard applications, LLMs, LangChain, vector databases, orchestration frameworks, and cloud-native services. You will be instrumental in operationalizing AI capabilities such as Conversational AI, Document Intelligence, Generative AI, and Agentic AI.

Key Responsibilities:

Architect & Build AI Solutions:

Design and implement backend systems using LangChain, RAG pipelines, and vector stores (e.g., FAISS, Pinecone, Weaviate).

Integrate LLMs (e.g., OpenAI, Gemini, Claude, Sonnet) with enterprise data sources and APIs.

Develop modular agents and assistants using LCNC platforms and agent builders or leverage in-app agents to orchestrate.

Platform Integration:

Connect AI services with cloud platforms (AWS Bedrock, Google Vertex AI, Azure AI).

Build and maintain AI Gateways (e.g., Kong) and orchestrate workflows via tools like n8n/Automation Anywhere/UIpath/Haystack.

Data & Model Management:

Implement secure access to internal/external data sources (data lakes, graphs, documents).

Collaborate with ML Ops teams to deploy, monitor, and optimize models.

Governance & Observability:

Ensure compliance with Responsible AI policies and integrate telemetry dashboards (e.g., Tableau).

Build telemetry dashboard as a single pane of glass for all AI implementations and support business and AI solutions' performance management, FinOps, usage tracking, and policy violation monitoring.

Collaboration & Enablement:

Work closely with developers, business AI Champions, IT and business users to translate requirements into scalable AI solutions.

Contribute to the development of custom AI apps and integrate with embedded/in-app AI features.

Required Qualifications:

• 2-5 years of backend engineering experience, with 2+ years in AI/ML systems.
• Proficiency in Python and frameworks like LangChain, FastAPI, Flask.
• Experience with LLM orchestration, RAG, and vector databases.
• Familiarity with cloud platforms (AWS, GCP, Azure) and AI services (Bedrock, Vertex, Firefly, Gemini).
• Strong understanding of API integration, IAM, and secure data access.
• Experience with ML Ops tools, context engineering, memory management – short term and long term, prompt engineering, and telemetry dashboards.
• Knowledge of enterprise architecture, semantic search, and document intelligence.

Preferred Skills:

• Experience with agentic AI frameworks and LCNC platforms.
• Familiarity with tools like Midjourney, Runway, dbt AI, Gemini Code Assist.
• Understanding of AI governance, compliance, and enterprise scaling strategies.
• Prior work in media, sports, or entertainment domains is a plus.